INDEX
Explanations
terms and phrases related to citizenship and immigration
New Auto-Interp
Negative Logits
antz
-0.17
dings
-0.17
hir
-0.16
yth
-0.16
fak
-0.15
crast
-0.15
ymoon
-0.15
Bever
-0.14
ilyn
-0.14
akit
-0.14
POSITIVE LOGITS
orus
0.16
æŀ
0.16
ni
0.15
کرÛĮ
0.14
524
0.14
Igor
0.14
áo
0.14
mgr
0.14
555
0.14
IColor
0.14
Activations Density 0.008%