INDEX
Explanations
references to the concept of 'body' in various contexts
New Auto-Interp
Negative Logits
ery
-0.19
leo
-0.18
erna
-0.18
umber
-0.17
hya
-0.16
staking
-0.16
ally
-0.16
ldkf
-0.15
qualities
-0.15
iban
-0.15
POSITIVE LOGITS
guards
0.38
guard
0.36
builder
0.30
politic
0.29
builders
0.28
weight
0.28
building
0.27
parts
0.23
wide
0.22
mind
0.22
Activations Density 0.042%