INDEX
Explanations
references to nationalities and political entities
New Auto-Interp
Negative Logits
intios
-0.58
Branche
-0.55
tagHelperRunner
-0.52
kissen
-0.52
Stirn
-0.51
noDo
-0.51
Biôgrafia
-0.50
usercontent
-0.50
delwed
-0.50
Билгалдахарш
-0.49
POSITIVE LOGITS
German
2.02
Germany
1.87
German
1.76
GERMAN
1.68
ドイツ
1.68
Germans
1.63
德国
1.63
Germany
1.62
german
1.57
немец
1.54
Activations Density 1.065%