INDEX
Explanations
mentions of whales and related marine life
New Auto-Interp
Negative Logits
zet
-0.19
ents
-0.15
itsu
-0.15
Burl
-0.15
Tiles
-0.15
obo
-0.15
_^
-0.14
ilim
-0.14
715
-0.14
-0.14
POSITIVE LOGITS
erp
0.19
ırı
0.17
athers
0.15
εÏģ
0.15
uids
0.15
ught
0.15
ableViewController
0.15
urgeon
0.15
landır
0.14
$MESS
0.14
Activations Density 0.008%