INDEX
Explanations
connections between emotions and personal experiences
New Auto-Interp
Negative Logits
ibold
-0.15
tread
-0.14
Stock
-0.14
alker
-0.13
McInt
-0.13
stav
-0.13
lsru
-0.13
iminal
-0.13
ballo
-0.13
ä»ģ
-0.13
POSITIVE LOGITS
okrat
0.18
InBackground
0.16
odash
0.16
jadx
0.15
æ´»
0.15
å¤ļ
0.15
compact
0.15
depr
0.15
ÅĤad
0.14
ych
0.14
Activations Density 0.056%