INDEX
Explanations
The neuron consistently activates on the second-person pronoun “you.”
New Auto-Interp
Negative Logits
hookers
-0.06
Mao
-0.06
武
-0.06
converters
-0.06
controls
-0.06
Province
-0.06
'utilisateur
-0.06
dh
-0.06
Bf
-0.06
allon
-0.06
POSITIVE LOGITS
_angle
0.07
.addChild
0.07
blok
0.07
�
0.07
bình
0.06
polygons
0.06
_insn
0.06
číslo
0.06
mapa
0.06
Seleccion
0.06
Activations Density 0.017%