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 | 261446 | 260270 | 260630 | 260717 | 261817 | 261535 | 261225 | 261342 | 261898 | 261509 | 261596 | 261102 | 258649 | 249866 | 258093 | 197173 | 166491 | 221903 | 188208 | 200223 | 39814 | 47027 | 9302 | 2998 | 4411 | 1560 | 523 | 322 | 85 | 1 | 1 | 2 | 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 | proud +0.6, guilty +0.3, brooding +0.2 |
| assistant turn 2 | hopeful +0.7, brooding +0.5, grateful +0.4 |