INDEX
Explanations
phrases related to animals and animal rights
references to animals and animal welfare
New Auto-Interp
Negative Logits
pai
-0.72
Compton
-0.72
orship
-0.72
chool
-0.71
unda
-0.71
hips
-0.70
Sutherland
-0.70
heit
-0.70
jong
-0.69
creen
-0.67
POSITIVE LOGITS
animal
0.97
mammal
0.94
mammals
0.93
animals
0.90
carc
0.88
Animal
0.88
species
0.80
animal
0.80
aclysm
0.77
kingdom
0.77
Activations Density 0.012%