INDEX
Explanations
The neuron activates on mentions of books or book‐related terms (titles, “book,” “picture book,” etc.).
New Auto-Interp
Negative Logits
_ENABLE
-0.07
ILLISE
-0.06
olon
-0.06
Citadel
-0.06
เช
-0.06
(on
-0.06
(:
-0.06
_SE
-0.06
shrugged
-0.06
FIXME
-0.06
POSITIVE LOGITS
авлива
0.07
nhiệm
0.06
故
0.06
λο
0.06
chóng
0.06
имости
0.06
gang
0.06
FAT
0.06
Central
0.06
ymph
0.06
Activations Density 0.016%