INDEX
Explanations
phrases related to sentencing and legal consequences
New Auto-Interp
Negative Logits
.AC
-0.15
kommen
-0.14
&action
-0.13
uxt
-0.13
usercontent
-0.13
RESSED
-0.13
woff
-0.13
setattr
-0.13
ì²Ń
-0.13
Ïħκ
-0.13
POSITIVE LOGITS
imprisonment
0.39
prison
0.39
jail
0.32
incarceration
0.32
sentence
0.32
sentences
0.31
term
0.30
imprison
0.30
confinement
0.29
concurrent
0.28
Activations Density 0.073%