INDEX
Explanations
mentions of pets and pet-related themes
New Auto-Interp
Negative Logits
hift
-0.17
hower
-0.15
idia
-0.15
VILLE
-0.15
leans
-0.15
adera
-0.15
/prom
-0.15
eron
-0.15
ieran
-0.15
fork
-0.14
POSITIVE LOGITS
ting
0.20
owners
0.19
companion
0.18
/small
0.18
/people
0.18
lovers
0.17
owners
0.17
Owners
0.17
apult
0.16
accompany
0.16
Activations Density 0.024%