INDEX
Explanations
references to wild pigs or diseases associated with them
New Auto-Interp
Negative Logits
estring
-0.15
جر
-0.15
moth
-0.15
enÃŃ
-0.15
.fx
-0.15
olicit
-0.15
ladu
-0.15
/loader
-0.15
اÙĦÙħÙĦ
-0.15
umble
-0.14
POSITIVE LOGITS
pig
0.67
Pig
0.62
pigs
0.59
pig
0.58
pork
0.53
Pork
0.47
çĮª
0.42
hog
0.41
sw
0.40
Hog
0.39
Activations Density 0.042%