INDEX
Explanations
sentiment and expressions of appreciation or enjoyment
New Auto-Interp
Negative Logits
orman
-0.15
tips
-0.15
Parties
-0.15
paged
-0.14
огÑĥ
-0.14
Palestin
-0.14
aine
-0.14
apan
-0.13
ä¼
-0.13
Bout
-0.13
POSITIVE LOGITS
اÙĨÛĮ
0.18
hazi
0.18
vä
0.15
Gardens
0.15
diss
0.15
OLON
0.15
.hs
0.14
Minimal
0.14
idor
0.14
UNCTION
0.14
Activations Density 0.103%