INDEX
Explanations
references to influential artists and art-related critiques
New Auto-Interp
Negative Logits
eniz
-0.16
tier
-0.15
hei
-0.14
asher
-0.14
eft
-0.14
ascar
-0.14
okie
-0.14
eking
-0.13
imbus
-0.13
omid
-0.13
POSITIVE LOGITS
oure
0.17
brtc
0.15
lok
0.15
dic
0.15
orp
0.14
.inc
0.14
undler
0.14
enz
0.14
æķĻ
0.14
<message
0.13
Activations Density 0.485%