INDEX
Explanations
instances of robbery, assaults, and violent crimes
New Auto-Interp
Negative Logits
Bomb
-0.16
piler
-0.15
630
-0.14
uestas
-0.14
apg
-0.14
åĿĬ
-0.14
olis
-0.14
462
-0.14
大人
-0.14
/AP
-0.14
POSITIVE LOGITS
esch
0.15
bles
0.14
Preis
0.14
Lust
0.13
manoe
0.13
èµ
0.13
Winner
0.13
кÑĥлÑı
0.13
Wikispecies
0.13
maneuvers
0.13
Activations Density 0.093%