INDEX
Explanations
phrases related to legal violations and gun-related incidents
New Auto-Interp
Negative Logits
emo
-0.16
izo
-0.15
uet
-0.15
aben
-0.15
ocket
-0.14
201
-0.14
pa
-0.14
onest
-0.14
duct
-0.14
loc
-0.14
POSITIVE LOGITS
/tos
0.16
imits
0.14
otomy
0.14
Äįe
0.14
disposing
0.13
Sharper
0.13
-haspopup
0.13
Brendan
0.13
ohl
0.13
anime
0.13
Activations Density 0.001%