INDEX
Explanations
expressions of desire and enjoyment related to experiences or activities
New Auto-Interp
Negative Logits
ÙĨص
-0.17
834
-0.17
defgroup
-0.15
644
-0.14
Ñij
-0.14
Shutterstock
-0.14
igo
-0.14
ricks
-0.14
Ø®Ùħ
-0.14
distances
-0.14
POSITIVE LOGITS
addictive
0.18
cean
0.16
lys
0.16
Cargo
0.15
want
0.15
wanting
0.15
Cargo
0.15
زÙĬد
0.14
wants
0.14
overdose
0.14
Activations Density 0.155%