INDEX
Explanations
phrases emphasizing ownership or possession
New Auto-Interp
Negative Logits
ulings
-0.16
hip
-0.16
çļĦåľ°æĸ¹
-0.15
à¹Įà¹Ĥ
-0.14
hips
-0.14
719
-0.14
Ãło
-0.14
egg
-0.14
ERY
-0.14
iae
-0.14
POSITIVE LOGITS
own
0.24
lef
0.20
iner
0.19
umblr
0.18
_own
0.17
ches
0.17
own
0.16
self
0.15
urre
0.15
sing
0.15
Activations Density 0.103%