INDEX
Explanations
expressions of physical touch and emotional connection
New Auto-Interp
Negative Logits
lug
-0.16
hug
-0.15
oblin
-0.15
handshake
-0.15
hugs
-0.14
å»Ĭ
-0.14
믿
-0.14
رÙĬÙģ
-0.14
rac
-0.13
vom
-0.13
POSITIVE LOGITS
possess
0.19
plunder
0.19
needy
0.19
heat
0.18
delicious
0.18
mo
0.17
Stroke
0.17
desire
0.17
press
0.16
ca
0.16
Activations Density 0.038%