INDEX
Explanations
specific attributes related to artworks or artistic items
New Auto-Interp
Negative Logits
плоÑī
-0.16
aina
-0.15
inda
-0.15
uplic
-0.15
inth
-0.15
/icons
-0.15
redient
-0.14
æĽ²
-0.14
ritel
-0.14
ãĥ¬ãĥ³
-0.14
POSITIVE LOGITS
вÑĢемÑı
0.20
колиÑĩеÑģÑĤво
0.19
дело
0.17
еÑģÑĤво
0.17
лиÑĨо
0.17
ÑģÑĢедÑģÑĤво
0.16
Ïīμα
0.16
mÄĽsto
0.16
знаÑĩение
0.16
ÑĢаÑģÑĤение
0.16
Activations Density 0.030%