INDEX
Negative Logits
yerləş
-0.09
cringe
-0.08
ingev
-0.08
entrando
-0.07
resalt
-0.07
povz
-0.07
redd
-0.07
potatoes
-0.07
상
-0.07
poter
-0.07
POSITIVE LOGITS
juggling
0.08
('*0.08
Photography
0.08
DIY
0.08
技巧
0.08
TECH
0.08
otics
0.07
Technique
0.07
insol
0.07
даг
0.07
Activations Density 0.010%