INDEX
Explanations
copyright information
references to copyright
New Auto-Interp
Negative Logits
adra
-0.78
arist
-0.77
oward
-0.73
ibur
-0.67
Lans
-0.67
ordinary
-0.67
Bere
-0.66
adows
-0.66
uten
-0.63
ild
-0.61
POSITIVE LOGITS
Copyright
1.25
yright
0.98
Copyright
0.98
©
0.86
ertodd
0.85
ulence
0.85
©
0.81
infringement
0.81
yrights
0.79
copyright
0.76
Activations Density 0.010%