INDEX
Explanations
references to animals, specifically birds, and their characteristics
New Auto-Interp
Negative Logits
Fus
-0.17
elsing
-0.16
kovi
-0.16
elay
-0.16
istor
-0.15
aleb
-0.15
lds
-0.15
enance
-0.15
Äijạo
-0.15
casting
-0.14
POSITIVE LOGITS
-headed
0.15
reich
0.15
oola
0.14
apo
0.14
inish
0.14
Resolve
0.14
bane
0.13
-shaped
0.13
IO
0.13
Verdana
0.13
Activations Density 0.448%