INDEX
Explanations
references to illegal activities, such as trade, drugs, smuggling, and weapons
terms related to illegal activities
New Auto-Interp
Negative Logits
oleon
-0.80
efully
-0.79
pread
-0.77
enger
-0.76
Remastered
-0.74
ritis
-0.72
oir
-0.71
igating
-0.70
Divinity
-0.69
ivities
-0.68
POSITIVE LOGITS
trafficking
0.93
substances
0.92
illegal
0.86
immigrant
0.85
drugs
0.83
downloading
0.82
immigrants
0.81
aliens
0.81
alien
0.80
ities
0.80
Activations Density 0.035%