INDEX
Explanations
phrases related to animal species and their characteristics
New Auto-Interp
Negative Logits
iy
-0.16
ury
-0.16
iol
-0.15
ahl
-0.14
ou
-0.14
ÑĢÑĥж
-0.14
bred
-0.14
loor
-0.13
177
-0.13
bre
-0.13
POSITIVE LOGITS
istrat
0.16
inar
0.16
psc
0.15
ónica
0.14
celik
0.14
quito
0.14
_trampoline
0.14
anean
0.14
0.14
atak
0.14
Activations Density 0.043%