INDEX
Explanations
names and surnames
occurrences of the name "Wang"
New Auto-Interp
Negative Logits
phia
-0.93
*/(
-0.72
byter
-0.70
pent
-0.69
Camden
-0.66
phis
-0.66
odic
-0.65
tarians
-0.63
tarian
-0.63
clair
-0.62
POSITIVE LOGITS
Wang
1.17
Bei
1.04
Fei
1.01
Chao
1.01
Jian
1.00
jing
0.99
wana
0.98
Xia
0.97
Zheng
0.96
zhou
0.93
Activations Density 0.007%