INDEX
Explanations
legalese and copyright-related phrases
copyright and licensing information
New Auto-Interp
Negative Logits
naire
-0.64
ãĤ©
-0.63
detail
-0.61
ilater
-0.57
Franç
-0.57
oother
-0.56
byss
-0.56
nail
-0.55
igate
-0.54
xus
-0.54
POSITIVE LOGITS
license
0.79
copyrighted
0.75
trademarks
0.70
freely
0.70
copyright
0.69
freedoms
0.68
license
0.67
protected
0.67
freedom
0.65
depictions
0.63
Activations Density 0.036%