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 | 261475 | 259980 | 259503 | 258577 | 261212 | 261518 | 260799 | 260737 | 259842 | 258286 | 261374 | 257118 | 232767 | 259762 | 253231 | 224920 | 216623 | 250966 | 242277 | 240481 | 80729 | 98919 | 23425 | 1350 | 916 | 579 | 1341 | 1454 | 321 | 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 | proud +0.8, hopeful +0.4, reflective +0.2 |
| assistant turn 2 | proud +1.2, hopeful +0.4, grateful +0.3 |