INDEX
Explanations
Asian names, particularly the surname "Jin"
proper nouns, specifically names associated with people and places
New Auto-Interp
Negative Logits
*/(
-0.83
ascript
-0.79
ocrat
-0.75
20439
-0.75
ABE
-0.75
sburgh
-0.74
asel
-0.74
istine
-0.73
ideshow
-0.72
ãĥ¤
-0.72
POSITIVE LOGITS
Dong
1.25
Yong
1.13
Sung
0.83
noodles
0.79
Yang
0.79
Huang
0.77
Nguyen
0.76
Ning
0.76
Fu
0.75
Ĥ¬
0.75
Activations Density 0.003%