INDEX
Explanations
concepts related to emotional experiences and personal growth
New Auto-Interp
Negative Logits
scene
-0.14
uis
-0.13
zcze
-0.13
_ARB
-0.13
彦
-0.13
thood
-0.13
arger
-0.12
.inputs
-0.12
yl
-0.12
ugo
-0.12
POSITIVE LOGITS
heart
0.35
hearts
0.34
-heart
0.31
Hearts
0.29
Heart
0.29
heart
0.27
Heart
0.26
mind
0.26
soul
0.26
Soul
0.25
Activations Density 0.185%