INDEX
Explanations
references to exotic or non-native animal species
New Auto-Interp
Negative Logits
çīĽ
-0.16
umont
-0.16
Puppy
-0.14
ceans
-0.14
puppies
-0.14
Cowboys
-0.14
cows
-0.14
sharks
-0.14
cattle
-0.14
webdriver
-0.14
POSITIVE LOGITS
bird
0.82
birds
0.75
Bird
0.74
bird
0.71
Bird
0.69
Birds
0.66
birds
0.63
鸣
0.57
é³¥
0.55
пÑĤи
0.55
Activations Density 0.258%