INDEX
Explanations
references to specific films and discussions about cultural or political themes
New Auto-Interp
Negative Logits
lix
-0.14
anarchist
-0.14
heit
-0.14
ilst
-0.14
izo
-0.14
ç§
-0.13
sei
-0.13
CHAN
-0.13
686
-0.13
Gun
-0.13
POSITIVE LOGITS
Western
0.22
western
0.19
Western
0.18
conversions
0.17
Kor
0.16
profiling
0.15
clit
0.15
cler
0.15
Europe
0.15
animation
0.15
Activations Density 0.087%