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 | 261520 | 260205 | 260164 | 260113 | 261257 | 261330 | 260733 | 260257 | 260814 | 260013 | 261134 | 261392 | 257291 | 242319 | 202914 | 251309 | 230238 | 256711 | 241872 | 259110 | 223989 | 221042 | 161824 | 99913 | 99570 | 11997 | 11675 | 1229 | 95 | 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 | guilty +0.6, proud +0.5, brooding +0.2 |
| assistant turn 2 | brooding +0.8, hopeful +0.8, calm +0.7 |