INDEX
Explanations
references to prehistoric sharks and their fossils
New Auto-Interp
Negative Logits
deer
-0.19
atak
-0.17
鹿
-0.15
ĵ
-0.15
unik
-0.15
ucc
-0.14
-stack
-0.14
Benedict
-0.14
cade
-0.14
Standing
-0.14
POSITIVE LOGITS
sharks
0.33
shark
0.32
Sharks
0.30
Shark
0.29
etooth
0.21
fin
0.20
fins
0.20
fin
0.19
Teeth
0.19
çīĻ
0.19
Activations Density 0.037%