INDEX
Explanations
mentions of U.S. Immigration and Customs Enforcement (ICE) and related entities
references to immigration enforcement agencies and their actions
New Auto-Interp
Negative Logits
itiveness
-0.61
ACTIONS
-0.60
ĵĺ
-0.59
trial
-0.55
grooming
-0.54
natureconservancy
-0.53
acles
-0.50
doors
-0.50
scrolls
-0.49
squares
-0.47
POSITIVE LOGITS
etus
0.69
Lenin
0.64
è¦ļéĨĴ
0.62
ãĥ¼ãĥ
0.60
uala
0.59
Clar
0.56
ucc
0.55
querque
0.55
ļé
0.54
ibrary
0.54
Activations Density 1.137%