INDEX
Explanations
references to guns and gun-related terms
New Auto-Interp
Negative Logits
Higgins
-0.16
usz
-0.16
quina
-0.15
æĬľ
-0.14
thinkable
-0.14
enance
-0.14
incinn
-0.14
tml
-0.14
à¥įà¤Łà¤®
-0.14
wich
-0.13
POSITIVE LOGITS
eldom
0.17
æk
0.17
desn
0.16
ergy
0.16
LOGGER
0.15
McInt
0.15
ivent
0.15
ssue
0.14
ultiply
0.14
nist
0.14
Activations Density 0.028%