INDEX
Explanations
instances of organizations or groups with the word "Front" in their name
references to various political organizations and movements
New Auto-Interp
Negative Logits
awk
-0.86
awks
-0.82
ilk
-0.80
STEM
-0.77
女
-0.76
UGH
-0.75
risome
-0.72
cles
-0.72
gging
-0.72
ike
-0.71
POSITIVE LOGITS
alis
0.84
ois
0.71
Front
0.68
Against
0.68
ing
0.68
icia
0.67
eering
0.67
iers
0.65
Phant
0.65
eous
0.65
Activations Density 0.012%