INDEX
Explanations
references to South Korea
references to Korea and related geographical or political contexts
New Auto-Interp
Negative Logits
llo
-0.79
MENTS
-0.78
Mayweather
-0.77
ashtra
-0.76
yard
-0.72
instein
-0.72
ttes
-0.72
MENT
-0.71
eus
-0.71
gerald
-0.70
POSITIVE LOGITS
orea
1.14
peninsula
1.08
ë
0.97
ì
0.97
Korea
0.96
Peninsula
0.92
ë
0.91
Koreans
0.84
Korean
0.83
Jong
0.82
Activations Density 0.029%