INDEX
Explanations
mentions of prominent actors or actresses in film discussions
New Auto-Interp
Negative Logits
igel
-0.17
iais
-0.16
itoris
-0.16
arpa
-0.15
amer
-0.15
eren
-0.14
onen
-0.14
_TV
-0.14
ypse
-0.14
quer
-0.14
POSITIVE LOGITS
dead
0.17
dead
0.17
tit
0.16
icode
0.15
çĸ
0.14
cul
0.14
guest
0.14
roster
0.14
legends
0.14
аÑĢÑĮ
0.14
Activations Density 0.093%