INDEX
Explanations
phrases involving the act of posing or positioning, particularly in relation to people and images
New Auto-Interp
Negative Logits
sh
-0.16
ugo
-0.15
auga
-0.15
UTC
-0.15
ola
-0.15
Goth
-0.15
uet
-0.15
uir
-0.15
uga
-0.14
zeug
-0.14
POSITIVE LOGITS
idon
0.21
pose
0.16
questions
0.15
yonel
0.15
Selectors
0.14
=pos
0.14
ekk
0.14
natal
0.14
question
0.14
threat
0.14
Activations Density 0.030%