INDEX
Explanations
terms related to immigration
references to immigration
New Auto-Interp
Negative Logits
sonian
-0.92
olls
-0.84
ilts
-0.82
çͰ
-0.78
eenth
-0.78
Ü
-0.78
obyl
-0.77
MpServer
-0.77
@#&
-0.75
aken
-0.74
POSITIVE LOGITS
detention
1.10
Detention
0.94
immigration
0.92
detain
0.90
deportation
0.90
visas
0.90
enforcement
0.88
reform
0.88
immigrants
0.86
enforcement
0.84
Activations Density 0.033%