INDEX
Explanations
phrases related to complex emotions and introspective thoughts
New Auto-Interp
Negative Logits
essler
-0.16
omi
-0.16
eldon
-0.14
991
-0.14
aeda
-0.14
ling
-0.14
halb
-0.13
OTHER
-0.13
848
-0.13
khá»ıi
-0.13
POSITIVE LOGITS
proceedings
0.28
everything
0.25
ä¸ĢåĪĩ
0.24
everything
0.23
tudo
0.22
ello
0.20
Everything
0.20
things
0.20
alles
0.19
Everything
0.18
Activations Density 0.528%