INDEX
Explanations
names of Chinese descent with the letter 'Z' and slightly lower activation for names with 'X'
names of individuals related to a specific context or event
New Auto-Interp
Negative Logits
Hitchcock
-0.75
parole
-0.72
phia
-0.69
nick
-0.68
ords
-0.67
*/(
-0.66
replay
-0.66
Phillies
-0.66
Montgomery
-0.65
NIGHT
-0.64
POSITIVE LOGITS
Xia
1.41
Yuan
1.39
jiang
1.38
Jing
1.36
wei
1.35
Xiang
1.30
Tian
1.30
Guang
1.29
Jiang
1.29
jing
1.26
Activations Density 0.040%