INDEX
Explanations
references to societal reintegration processes for individuals transitioning out of institutions
New Auto-Interp
Negative Logits
opol
-0.18
verter
-0.16
airo
-0.15
bev
-0.15
oured
-0.14
rapper
-0.14
visor
-0.13
__,__
-0.13
peech
-0.13
anela
-0.13
POSITIVE LOGITS
etheless
0.18
æĿ¥è¯´
0.17
uably
0.17
ely
0.17
edly
0.16
ãĤ¯ãĥĪ
0.15
ingly
0.15
обÑĢазом
0.15
locker
0.14
.ly
0.14
Activations Density 0.792%