INDEX
Explanations
phrases related to deportation
terms related to deportation and immigration enforcement
New Auto-Interp
Negative Logits
oken
-0.78
Downloadha
-0.72
aque
-0.72
oof
-0.69
ournals
-0.69
pering
-0.69
jac
-0.69
Attribution
-0.67
soDeliveryDate
-0.67
PsyNet
-0.67
POSITIVE LOGITS
deported
1.18
deport
1.04
deportation
0.94
detain
0.89
detention
0.81
fug
0.80
chwitz
0.77
ploy
0.76
aliens
0.74
terrorist
0.71
Activations Density 0.032%