INDEX
Explanations
references to political or legal figures and events
New Auto-Interp
Negative Logits
ÑijÑĢ
-0.16
Campo
-0.16
maduras
-0.15
rames
-0.15
stellen
-0.14
ubber
-0.14
/dat
-0.14
(et
-0.14
æİª
-0.14
lsen
-0.14
POSITIVE LOGITS
legal
0.16
Dud
0.16
exile
0.15
Ordering
0.15
passport
0.15
agua
0.15
immunity
0.15
ex
0.15
pel
0.14
izr
0.14
Activations Density 0.031%