INDEX
Negative Logits
igor
-0.07
pesticides
-0.06
Tob
-0.06
_CTL
-0.06
bd
-0.06
Laurie
-0.06
Handles
-0.06
�ん
-0.06
spec
-0.06
sender
-0.06
POSITIVE LOGITS
verschill
0.06
apartment
0.06
giành
0.06
города
0.06
(completion
0.06
arson
0.06
یاد
0.06
intertwined
0.06
Light
0.06
(plot
0.06
Activations Density 0.001%