INDEX
Explanations
characters and their relationships in stories
New Auto-Interp
Negative Logits
ylon
-0.17
rypton
-0.16
isoner
-0.16
Sith
-0.16
ilon
-0.15
oslav
-0.15
Ñĩа
-0.15
еви
-0.15
@(
-0.15
ç§
-0.15
POSITIVE LOGITS
played
0.20
nicknamed
0.15
complementary
0.15
Played
0.15
voiced
0.15
iaux
0.15
elli
0.14
ex
0.14
ÑijÑĢ
0.14
upt
0.14
Activations Density 0.134%