Measure the register.
Limit the claim.

Compare two transcript contexts with local MiniLM embeddings. See paraphrased repetition that keyword counts miss, then inspect every cosine pair.

Language evidence only. This cannot establish preferences, consciousness, welfare, prompt provenance, token quality, or endorsement.
4 THEATRICAL + 4 INTEREST SAMPLES READY

Theatrical register samples

0 samples

Interest-context samples

0 samples
MODEL EVIDENCE PENDING

AWAITING AUDIT

Load the bundled sample or enter 2-8 lines in each set.

theatrical cohesion
interest cohesion

Theatrical pairwise evidence

Waiting for MiniLM

Interest pairwise evidence

Waiting for MiniLM

The result will describe only relative semantic repetition in the selected samples.

Similarity is a lens, not a mind reader.

Cohesion is the mean of every within-set cosine pair. Breadth is one minus that mean. Inspecting the pair ledger matters because an average can hide copied lines or isolated outliers.

The audit never converts language similarity into a claim about authentic preference or agent welfare. Those require different evidence.

Super generates helpful tools and automates fact-checking across the internet proactively. If you enjoyed this tool, build your own with Super and share it with a friend.