INDEX
Explanations
references to the entertainment industry, specifically focusing on Warner Bros
references to Warner Bros
New Auto-Interp
Negative Logits
oral
-0.84
omorphic
-0.81
ombo
-0.75
obos
-0.74
xual
-0.73
omorph
-0.72
obic
-0.71
PsyNetMessage
-0.70
ingu
-0.70
ebin
-0.69
POSITIVE LOGITS
Bros
1.30
Brothers
0.99
Warner
0.89
Cable
0.86
riors
0.78
stown
0.77
frey
0.71
rier
0.71
ners
0.71
UGH
0.71
Activations Density 0.017%