INDEX
Explanations
references to incarceration and imprisonment
New Auto-Interp
Negative Logits
.synthetic
-0.16
YTE
-0.15
tered
-0.14
Prest
-0.14
493
-0.14
ipc
-0.14
ierz
-0.13
اÙĦتÙĤ
-0.13
ISTER
-0.13
906
-0.13
POSITIVE LOGITS
CCI
0.18
OnInit
0.17
urm
0.17
elen
0.16
ULSE
0.16
linkplain
0.16
uraa
0.14
Göz
0.14
odia
0.14
licken
0.14
Activations Density 0.057%