INDEX
Explanations
references to media-related topics and discussions about body image and self-acceptance
New Auto-Interp
Negative Logits
ahat
-0.19
ç©´
-0.16
/node
-0.15
ienne
-0.15
utton
-0.15
obo
-0.15
ç¿Ķ
-0.14
.elementAt
-0.13
lái
-0.13
struction
-0.13
POSITIVE LOGITS
BBC
0.32
bbc
0.28
BBC
0.27
CBC
0.20
972
0.19
bbc
0.18
endance
0.17
wers
0.16
US
0.16
993
0.16
Activations Density 0.023%