INDEX
Explanations
expressions of sentiment related to experiences and emotions
New Auto-Interp
Negative Logits
ernaut
-0.16
uars
-0.15
chet
-0.14
殿
-0.14
imd
-0.14
embros
-0.14
imler
-0.14
ionario
-0.14
uner
-0.13
dera
-0.13
POSITIVE LOGITS
yo
0.15
Must
0.14
AINED
0.14
orer
0.14
Gallery
0.13
adm
0.13
šak
0.13
avicon
0.13
AVA
0.13
359
0.13
Activations Density 0.353%