INDEX
Explanations
topics related to body image and positivity
New Auto-Interp
Negative Logits
homosexual
-0.15
Geoff
-0.15
homosexuals
-0.14
sentimental
-0.14
ocop
-0.14
á¹
-0.13
mux
-0.13
ustomed
-0.13
çĿĽ
-0.13
]={↵-0.13
POSITIVE LOGITS
body
0.33
beauty
0.32
Beauty
0.28
Body
0.27
Beauty
0.26
physique
0.25
BODY
0.24
Body
0.24
bodies
0.24
/body
0.24
Activations Density 0.056%