INDEX
Explanations
terms and phrases related to immigration and citizenship
New Auto-Interp
Negative Logits
_ipv
-0.15
manship
-0.15
imony
-0.15
à¹Ĩ
-0.15
cher
-0.15
_migration
-0.14
immun
-0.14
Denn
-0.14
eteria
-0.14
NESS
-0.14
POSITIVE LOGITS
reform
0.20
/custom
0.20
-control
0.19
restriction
0.19
-related
0.19
/ref
0.18
Reform
0.18
detention
0.18
control
0.18
status
0.18
Activations Density 0.008%