INDEX
Explanations
references to Jewish identity and historical events related to Jews
New Auto-Interp
Negative Logits
Jefus
-0.76
Galer
-0.71
Theſe
-0.70
-0.69
degrad
-0.69
Савезне
-0.68
Phry
-0.67
Efq
-0.66
Personensuche
-0.65
|}{}-0.65
POSITIVE LOGITS
Jewish
1.37
Jews
1.22
Jewish
1.16
synagogue
1.00
Jews
1.00
jewish
0.99
Aviv
0.96
jewish
0.95
Synagogue
0.94
Israel
0.91
Activations Density 0.216%