INDEX
Explanations
terms related to the "alt-right"
references to the alt-right movement
New Auto-Interp
Negative Logits
hips
-0.79
loo
-0.78
ecause
-0.74
bah
-0.70
EEE
-0.69
Affect
-0.69
LOCK
-0.65
ilk
-0.65
interrupted
-0.65
atche
-0.64
POSITIVE LOGITS
itud
1.13
itudes
1.07
alt
0.96
itudinal
0.93
ogether
0.84
itude
0.82
imeter
0.74
ifa
0.74
ascend
0.74
cult
0.74
Activations Density 0.011%