INDEX
Negative Logits
entdeckt
-0.09
ontdekt
-0.09
discoveries
-0.09
-0.08
GAIN
-0.08
gone
-0.07
Govern
-0.07
discover
-0.07
_checked
-0.07
дағы
-0.07
POSITIVE LOGITS
afi
0.08
parcel
0.08
mahal
0.08
leme
0.07
0.07
تجاه
0.07
)!=
0.07
fie
0.07
china
0.07
kile
0.07
Activations Density 0.018%