INDEX
Explanations
words related to different types of birds
references to birds in various contexts
New Auto-Interp
Negative Logits
idates
-0.71
avez
-0.70
idential
-0.69
FINE
-0.67
Wr
-0.65
Nex
-0.65
imaru
-0.63
Registrar
-0.63
xia
-0.62
urdue
-0.62
POSITIVE LOGITS
birds
1.17
bird
1.17
birds
1.05
Birds
1.02
bats
0.98
osaurs
0.94
seed
0.94
irds
0.92
species
0.92
owl
0.92
Activations Density 0.005%