INDEX
Explanations
references to various species of animals, particularly elephants and marine life
New Auto-Interp
Negative Logits
podob
-0.18
vais
-0.17
braco
-0.17
ONO
-0.17
ICY
-0.16
efe
-0.16
ço
-0.16
uctor
-0.16
brero
-0.16
stants
-0.15
POSITIVE LOGITS
able
0.17
imper
0.16
inhab
0.15
il
0.15
mental
0.15
Next
0.15
found
0.15
Aut
0.15
Patton
0.14
ret
0.14
Activations Density 0.049%