INDEX
Explanations
breeds of dogs
words related to animal adoption and specific breeds or types of pets
New Auto-Interp
Negative Logits
Shap
-0.80
ioxide
-0.80
unda
-0.75
çķ
-0.73
Petroleum
-0.72
stanbul
-0.71
princ
-0.67
obin
-0.66
Lumin
-0.66
lawy
-0.65
POSITIVE LOGITS
puppies
1.22
pets
1.14
puppy
1.13
pup
1.05
animals
1.02
kittens
0.99
dogs
0.97
euth
0.93
paws
0.89
zoo
0.88
Activations Density 0.169%