INDEX
Explanations
phrases related to body parts, specifically legs
references to legs
New Auto-Interp
Negative Logits
NEWS
-0.80
Published
-0.76
AMI
-0.67
VERTIS
-0.65
chie
-0.63
Recommend
-0.63
retrospective
-0.63
æ©
-0.62
COMPLE
-0.62
Destination
-0.61
POSITIVE LOGITS
legs
1.20
Legs
1.03
fins
0.95
puter
0.94
thighs
0.94
guards
0.92
skirts
0.87
weed
0.86
pread
0.86
torso
0.80
Activations Density 0.009%