INDEX
Explanations
references to firearms and gun-related terminology
New Auto-Interp
Negative Logits
alm
-0.16
WARE
-0.16
ByUrl
-0.15
обов
-0.14
oge
-0.14
942
-0.14
agus
-0.14
ë°ķ
-0.14
agini
-0.14
ante
-0.14
POSITIVE LOGITS
ipher
0.19
fighter
0.17
mith
0.17
Lor
0.16
anim
0.15
arel
0.15
elop
0.15
claimer
0.15
beck
0.15
ysis
0.14
Activations Density 0.016%