INDEX
Explanations
terms related to incarceration and sentencing in prison contexts
New Auto-Interp
Negative Logits
ajan
-0.16
iscrimination
-0.15
paren
-0.15
imple
-0.15
æį
-0.14
ertility
-0.14
ÑĸÑĩна
-0.14
ALERT
-0.13
ahun
-0.13
_PIPE
-0.13
POSITIVE LOGITS
ensus
0.15
ãĥ©ãĥ¼
0.15
raquo
0.15
EEK
0.14
ergus
0.14
desert
0.14
erator
0.14
odial
0.14
pper
0.14
bard
0.14
Activations Density 0.264%