INDEX
Explanations
themes related to personal relationships and emotional dynamics
New Auto-Interp
Negative Logits
对æĸ¹
-0.17
SEL
-0.15
isser
-0.14
ACHI
-0.14
Äħ
-0.14
agh
-0.14
ukan
-0.13
OptionsMenu
-0.13
enemy
-0.13
uy
-0.13
POSITIVE LOGITS
me
0.37
us
0.31
my
0.31
æĪij
0.30
mine
0.27
myself
0.26
æĪijçļĦ
0.25
my
0.24
æĪij
0.24
менÑı
0.24
Activations Density 0.394%