INDEX
Explanations
body parts and their states
New Auto-Interp
Negative Logits
arg
0.36
自分の
0.34
精神
0.31
নিজেদের
0.31
Mental
0.31
Mình
0.30
瀵
0.30
Personal
0.29
मानसिक
0.29
ambil
0.29
POSITIVE LOGITS
clad
0.43
adorned
0.43
betray
0.40
plastered
0.38
trained
0.37
accustomed
0.36
encased
0.34
pits
0.33
traitor
0.33
scarred
0.33
Activations Density 0.087%