INDEX
Explanations
mentions of specific animal species
New Auto-Interp
Negative Logits
shadow
-0.17
shadow
-0.17
Bug
-0.16
shade
-0.16
Bug
-0.16
uden
-0.16
mosquito
-0.16
swamp
-0.16
illes
-0.16
elier
-0.16
POSITIVE LOGITS
tern
0.26
seals
0.25
sku
0.24
seal
0.23
colonies
0.23
gu
0.22
Penguin
0.22
boob
0.22
Guil
0.22
seab
0.21
Activations Density 0.015%