INDEX
Explanations
references to anti-Semitism and associated controversies
New Auto-Interp
Negative Logits
opoulos
-0.15
vale
-0.15
ÑĤÑĮ
-0.15
ĽĦ
-0.14
pper
-0.14
lete
-0.14
OSC
-0.14
nom
-0.14
lán
-0.14
ÙĪØ¹
-0.14
POSITIVE LOGITS
Israel
0.24
CAMERA
0.22
Holocaust
0.21
Jews
0.21
Israel
0.21
Israeli
0.21
Palestine
0.20
Jew
0.20
Jewish
0.20
BDS
0.19
Activations Density 0.046%