INDEX
Explanations
references to pigs and pig-related terms
New Auto-Interp
Negative Logits
.nih
-0.15
cat
-0.15
ixa
-0.14
uka
-0.14
Downs
-0.14
rive
-0.14
vala
-0.14
orte
-0.14
edia
-0.14
CAT
-0.14
POSITIVE LOGITS
pig
0.32
pig
0.31
gy
0.29
Pig
0.29
pigs
0.26
pork
0.23
sty
0.21
çĮª
0.20
sque
0.18
Pork
0.18
Activations Density 0.014%