INDEX
Explanations
mentions of dolphins
mentions of dolphins or related marine animals
New Auto-Interp
Negative Logits
Interstitial
-0.89
Flavoring
-0.70
âĶģ
-0.70
ãĥ´ãĤ¡
-0.68
ablishment
-0.66
ures
-0.66
DIR
-0.66
ISTER
-0.65
ür
-0.64
IELD
-0.64
POSITIVE LOGITS
dolphin
1.26
dolphins
1.12
whale
1.09
iform
1.01
arium
0.95
odon
0.95
whales
0.89
fish
0.84
olphin
0.83
squid
0.74
Activations Density 0.008%