INDEX
Explanations
mentions of alt-right ideology and related terms
references to the alt-right movement
New Auto-Interp
Negative Logits
loo
-0.78
ecause
-0.75
hips
-0.70
enegger
-0.68
BLE
-0.66
manship
-0.66
è»
-0.65
士
-0.64
EEE
-0.63
SG
-0.63
POSITIVE LOGITS
itud
1.29
ogether
1.26
itudes
1.25
itude
1.24
itudinal
1.08
imore
1.00
uve
0.92
imeter
0.86
imately
0.84
ough
0.82
Activations Density 0.017%