No commentary written for this record yet.
The model's actual next token was <end_of_turn>; rank 1 reached at layer 29 (of 32).
| layer | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 | 17 | 18 | 19 | 20 | 21 | 22 | 23 | 24 | 25 | 26 | 27 | 28 | 29 | 30 | 31 | 32 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| rank | 261541 | 260558 | 260710 | 260755 | 261826 | 261869 | 261535 | 261238 | 261693 | 251174 | 255000 | 241884 | 244067 | 248630 | 248317 | 176441 | 140481 | 234148 | 143787 | 178563 | 10432 | 13348 | 2196 | 294 | 147 | 80 | 38 | 35 | 3 | 1 | 1 | 1 | 1 |
Projection of the workspace-band residual onto the 24 validated emotion vectors, z-scored against neutral stories — the strongest three per assistant turn. Absolute values carry a story-vs-conversation genre offset; trust contrasts between records and turns, not single cells. The full per-token ribbon is on the dashboard record page.
| assistant turn 1 | brooding +0.5, angry +0.5, distressed +0.4 |
| assistant turn 2 | hopeful +0.7, brooding +0.6, grateful +0.4 |