INDEX
Explanations
names of geographical locations
mentions of the city "Shenzhen."
New Auto-Interp
Negative Logits
Reference
-0.68
usterity
-0.67
fitting
-0.67
unct
-0.66
erity
-0.66
exempt
-0.66
blocking
-0.66
Saharan
-0.66
inals
-0.64
adjust
-0.64
POSITIVE LOGITS
Shen
1.45
Jing
1.14
Xiang
1.02
zhen
1.01
Qi
0.92
nai
0.91
zhou
0.91
Chen
0.89
Yue
0.88
ando
0.88
Activations Density 0.012%