INDEX
Explanations
copyright and legal notices
New Auto-Interp
Negative Logits
Bu
-0.17
pl
-0.17
ple
-0.15
-0.15
iesz
-0.15
rove
-0.14
Hal
-0.14
pr
-0.14
cko
-0.14
in
-0.14
POSITIVE LOGITS
copyright
0.46
Copyright
0.45
Copyright
0.45
copyright
0.44
opyright
0.41
COPYRIGHT
0.39
©
0.38
copyrights
0.36
©
0.34
copyrighted
0.32
Activations Density 0.178%