INDEX
Explanations
references to Iran and its historical or political context
New Auto-Interp
Negative Logits
engin
-0.15
LIK
-0.15
laut
-0.15
undy
-0.15
visa
-0.15
eton
-0.14
igs
-0.13
Sayı
-0.13
anges
-0.13
ÂŁ
-0.13
POSITIVE LOGITS
Sunder
0.14
anoi
0.14
ahas
0.14
æĺŃåĴĮ
0.14
defaultCenter
0.14
ano
0.14
oksen
0.14
hoog
0.13
Ñĥг
0.13
ailable
0.13
Activations Density 0.135%