INDEX
Explanations
references to Israel and its geopolitical issues, particularly in relation to Jewish identity and security
New Auto-Interp
Negative Logits
askell
-0.16
utsche
-0.15
yw
-0.15
поÑĩ
-0.15
sta
-0.15
gii
-0.15
ká
-0.15
.tables
-0.14
esto
-0.14
akt
-0.14
POSITIVE LOGITS
661
0.15
enco
0.15
обÑĢеÑĤ
0.14
Porter
0.14
Shel
0.14
fully
0.13
ÄĻd
0.13
_sun
0.13
imary
0.13
.orig
0.13
Activations Density 0.036%