Loading recorded reports…
Whisper Tiny · decoder evidence
Watch a transcript become readable through depth.
Three frozen ASR runs show early readability, late emergence, and tokenizer-piece behavior. Select a report, then hover or focus any layer slice for its exact rank and probability.
Lower rank is stronger readability. The final HEAD slice is the model's actual output distribution; earlier slices are fitted readouts.
READING BOUNDARY
What this lens can—and cannot—say
Rank measures readability. It asks where the realized output sits in a fitted vocabulary-wide readout at a layer.
Rank is not calibrated confidence. A strong intermediate rank does not prove conscious consideration, causation, or correctness.
Errors remain evidence. Generated paths, reference mismatches, token boundaries, and held-out status stay visible in each report.