INDEX
Explanations
references to the name "Han" and its variations in context
New Auto-Interp
Negative Logits
134
-0.20
nego
-0.16
iard
-0.15
zin
-0.14
elles
-0.14
_Callback
-0.14
154
-0.14
135
-0.14
cht
-0.14
erset
-0.14
POSITIVE LOGITS
Solo
0.29
over
0.28
ibal
0.25
Solo
0.24
solo
0.21
uman
0.20
OVER
0.20
lon
0.19
ania
0.18
ım
0.17
Activations Density 0.007%