INDEX
Explanations
proper nouns related to a specific company
mentions of the Warner Bros. company
New Auto-Interp
Negative Logits
oral
-0.83
ebin
-0.78
sembly
-0.78
idences
-0.75
xual
-0.73
bered
-0.72
yip
-0.71
ombo
-0.71
obos
-0.69
sshd
-0.69
POSITIVE LOGITS
Bros
1.24
Warner
1.04
Brothers
0.96
Thor
0.83
frey
0.76
Cable
0.74
Film
0.73
iage
0.72
stown
0.70
sonian
0.70
Activations Density 0.010%