INDEX
Explanations
words related to fictional creatures or characters
mentions of characters in a specific video game
New Auto-Interp
Negative Logits
validated
-0.61
exercise
-0.60
dentist
-0.58
trademark
-0.58
list
-0.57
post
-0.57
perm
-0.56
sadd
-0.55
Acc
-0.55
99
-0.55
POSITIVE LOGITS
lings
4.89
ling
2.14
lers
1.58
lins
1.41
glers
1.20
worms
1.19
tones
1.12
nings
1.11
ings
1.11
lords
1.09
Activations Density 0.006%