INDEX
Explanations
references to gun laws and regulations
New Auto-Interp
Negative Logits
ichert
-0.16
shint
-0.15
md
-0.15
_IRQ
-0.15
меÑĩ
-0.14
Sher
-0.14
stain
-0.14
бÑĥÑĢг
-0.14
Bur
-0.14
impl
-0.14
POSITIVE LOGITS
akin
0.17
732
0.16
work
0.15
657
0.14
://
0.14
735
0.14
empt
0.13
oper
0.13
965
0.13
REAM
0.13
Activations Density 0.311%