INDEX
Explanations
references to art and artistic techniques
New Auto-Interp
Negative Logits
æ±½
-0.16
WW
-0.15
Libertarian
-0.15
Grammy
-0.15
Artifact
-0.14
192
-0.14
189
-0.14
194
-0.14
.inst
-0.13
Democracy
-0.13
POSITIVE LOGITS
Flem
0.25
Tit
0.23
portrait
0.23
Raphael
0.23
Rub
0.23
portraits
0.23
oil
0.22
painted
0.22
painting
0.21
Portrait
0.21
Activations Density 0.037%