INDEX
Explanations
names of historical figures associated with art and architecture
New Auto-Interp
Negative Logits
inspace
-0.18
bcm
-0.15
ichert
-0.15
okol
-0.15
ayan
-0.15
ypi
-0.14
ograms
-0.14
شد
-0.14
акон
-0.14
okay
-0.14
POSITIVE LOGITS
Ney
0.16
ÑĢовиÑĩ
0.16
ân
0.14
صرÙģ
0.14
eson
0.14
pter
0.13
ãĥĻ
0.13
ç²¾
0.13
ditor
0.13
orph
0.13
Activations Density 0.236%