INDEX
Explanations
references to the concept of "body" in various contexts
New Auto-Interp
Negative Logits
svp
-0.16
stin
-0.16
Stub
-0.14
erosis
-0.14
coh
-0.14
iba
-0.14
born
-0.14
erie
-0.14
atio
-0.14
abilit
-0.14
POSITIVE LOGITS
guards
0.23
guard
0.20
weight
0.19
/body
0.18
pháºŃn
0.16
wide
0.15
-body
0.15
gest
0.15
-wide
0.14
-earth
0.14
Activations Density 0.048%