INDEX
Explanations
references to "Bat" or "bat," likely in the context of the character or concept in popular culture
New Auto-Interp
Negative Logits
hoff
-0.22
nees
-0.17
.nih
-0.16
nces
-0.16
idge
-0.16
adoo
-0.16
oras
-0.15
VML
-0.15
aceut
-0.15
Vit
-0.15
POSITIVE LOGITS
htub
0.29
avia
0.25
wing
0.24
lle
0.22
eman
0.20
ista
0.20
ting
0.19
ht
0.19
girl
0.18
ignal
0.18
Activations Density 0.009%