INDEX
Explanations
references to pets, specifically cats and dogs
New Auto-Interp
Negative Logits
reed
-0.17
оÑĢод
-0.16
ierz
-0.15
izards
-0.15
олÑİ
-0.15
phinx
-0.15
æļ
-0.14
iali
-0.14
Arena
-0.14
zial
-0.14
POSITIVE LOGITS
Big
0.19
Miss
0.19
Mr
0.18
Big
0.18
mr
0.17
Spark
0.17
Chief
0.17
_mr
0.17
MISS
0.17
Mr
0.17
Activations Density 0.326%