INDEX
Explanations
references to people or pronouns in various languages
New Auto-Interp
Negative Logits
EndInit
-0.83
таратура
-0.79
esgue
-0.78
Wikimédia
-0.76
'{@-0.72
بوابة
-0.72
Välislingid
-0.71
AnchorStyles
-0.69
tvr
-0.68
DrawerToggle
-0.66
POSITIVE LOGITS
Он
1.42
он
1.42
Он
1.36
Оно
1.23
ela
1.17
она
1.17
оно
1.15
eles
1.13
ele
1.10
ellos
1.06
Activations Density 0.034%