INDEX
Explanations
names of people, particularly in entertainment or celebrity contexts
New Auto-Interp
Negative Logits
“
-0.50
-0.50
"
-0.49
A
-0.49
,
-0.47
-0.47
↵
-0.47
↵↵
-0.46
addContainerGap
-0.44
au
-0.44
POSITIVE LOGITS
ModelExpression
1.05
korean
0.95
Seoul
0.94
Koreans
0.94
Korean
0.91
korea
0.90
Korean
0.89
Busan
0.88
Korea
0.88
Seoul
0.85
Activations Density 1.636%