User Rating 0.0
Total Usage 0 times
Text Input
0 words
Analysis Report WAITING
Likely Human Likely AI
0% AI Probability Score
Burstiness (σ) - Sentence Length Var
Trigger Density 0 AI Phrases Found
Avg Sentence - Words / Sentence
Readability - Flesch-Kincaid
Detected Patterns
No analysis yet
Structural X-Ray
AI Trigger Low Variance
Detailed sentence analysis will appear here...
Is this tool helpful?

Your feedback helps us improve.

About

This tool utilizes statistical linguistics and pattern recognition to evaluate text for characteristics common to Large Language Models (LLMs). Unlike human writing, which typically exhibits high entropy and distinct structural variance (burstiness), AI models tend to converge on probabilistic averages, resulting in smoother, more monotonous sentence structures.

The analysis relies on three core vectors: Perplexity Proxy (vocabulary complexity), Burstiness (sentence length variance), and Semantic Fingerprinting (identifying overused AI transition phrases). By measuring the deviation from natural human chaos, we can estimate the likelihood of machine generation without sending data to external servers.

ai-detector text-analysis writing-assistant seo-tools content-verification

Formulas

The core heuristic for detecting "robotic" uniformity is the Standard Deviation of sentence lengths, often referred to as Burstiness.

σ = Ni=1 (xi x)2N

Where xi is the length of sentence i, x is the average sentence length, and N is the total number of sentences.

Readability is calculated using the Flesch-Kincaid Grade Level formula:

Score = 0.39 (total wordstotal sentences) + 11.8 (total syllablestotal words) 15.59

Reference Data

MetricDefinitionAI CharacteristicHuman Characteristic
Burstiness (σ)Standard Deviation of Sentence LengthsLow (< 5 words). Consistent, rhythmic structure.High (> 10 words). Chaotic mix of short/long sentences.
Perplexity ProxyVocabulary Entropy & Rare Word DensityLow. Prefers high-probability tokens.High. Uses unexpected synonyms and idioms.
Repetition RateN-gram density (3-grams)High repetition of structural phrases.Low repetition, more organic flow.
Transition DensityFrequency of conjunctive adverbsHigh (e.g., "Moreover", "Furthermore").Moderate to Low.
Sentence Length (Avg)Mean words per sentence15-20 words (optimized for readability).Varies wildly (5 to 40+ words).

Frequently Asked Questions

Current LLMs (like GPT-4) have statistical biases towards certain connecting phrases and abstract nouns. Words like "tapestry", "landscape", "delve", and "seamless" appear with disproportionately high frequency in AI training data compared to natural human speech.
Not always. Highly formal academic writing or technical documentation often mimics low-burstiness patterns because it prioritizes clarity and consistency over stylistic flair. However, casual or creative writing with low burstiness is a strong indicator of AI generation.
No. This tool runs entirely in your browser using JavaScript. The text is analyzed locally on your device and is never sent to any server.
Heuristic detection is an estimation based on style patterns (syntax, structure, vocabulary). While it cannot "know" the origin with 100% certainty, it is highly effective at spotting the "default voice" of common AI models.