INDEX
Explanations
references to firearms and gun-related incidents
New Auto-Interp
Negative Logits
à¥įà¤ķर
-0.15
emes
-0.15
cher
-0.15
685
-0.14
kir
-0.14
664
-0.14
523
-0.14
Cyr
-0.13
è®
-0.13
ļ
-0.13
POSITIVE LOGITS
ivan
0.16
direction
0.15
ucks
0.15
_blank
0.15
Direction
0.15
Blank
0.15
ÄĻd
0.14
blanks
0.14
smÄĽrem
0.14
heits
0.14
Activations Density 0.073%