INDEX
Explanations
descriptions of design elements and aesthetic qualities
New Auto-Interp
Negative Logits
åºŃ
-0.17
ivia
-0.15
erve
-0.15
via
-0.15
adj
-0.14
auen
-0.14
contin
-0.14
acio
-0.14
duty
-0.14
vil
-0.14
POSITIVE LOGITS
AVE
0.16
OVE
0.16
traveler
0.14
extents
0.14
elian
0.14
Went
0.14
iel
0.14
kazy
0.14
iew
0.13
иÑĤов
0.13
Activations Density 0.036%