INDEX
Explanations
the name "Han" followed by a number
mentions of the name "Han."
New Auto-Interp
Negative Logits
pts
-0.73
therap
-0.69
pse
-0.69
rip
-0.67
itect
-0.67
EPS
-0.64
venom
-0.63
cape
-0.63
magnesium
-0.62
vic
-0.61
POSITIVE LOGITS
Han
3.79
Han
3.10
Hann
1.49
Leia
1.40
Wei
1.23
Hin
1.22
Gan
1.21
Mei
1.20
Guan
1.19
Zhao
1.18
Activations Density 0.016%