INDEX
Explanations
references to political candidates and election-related events
New Auto-Interp
Negative Logits
arken
-0.18
edef
-0.16
ile
-0.14
106
-0.13
otherwise
-0.13
ég
-0.13
yere
-0.13
اÙĦاÙĨ
-0.13
erno
-0.13
tslint
-0.13
POSITIVE LOGITS
utzer
0.16
олод
0.15
rosse
0.14
ATTER
0.14
gebra
0.14
Buen
0.14
ÙİØ¬
0.14
atrix
0.14
Group
0.13
azard
0.13
Activations Density 0.071%