INDEX
Explanations
terms related to "alt-right" and similar political movements
references to the "alt-right" political movement
New Auto-Interp
Negative Logits
loo
-0.75
hips
-0.74
EEE
-0.74
ecause
-0.73
LESS
-0.72
士
-0.71
Barn
-0.70
NING
-0.69
interrupted
-0.69
BLE
-0.67
POSITIVE LOGITS
itud
1.03
itudes
1.00
alt
0.97
ogether
0.88
imore
0.87
itude
0.85
ascend
0.81
icter
0.79
itudinal
0.78
cult
0.75
Activations Density 0.008%