INDEX
Explanations
mentions of artists and their works
New Auto-Interp
Negative Logits
çĶ
-0.17
etro
-0.16
anzi
-0.15
å±Ģ
-0.15
WI
-0.14
property
-0.14
((__
-0.14
Garten
-0.13
sister
-0.13
owe
-0.13
POSITIVE LOGITS
uar
0.15
mith
0.14
COMP
0.14
mitt
0.14
mit
0.14
ewis
0.14
Leer
0.14
vä
0.14
nost
0.13
alom
0.13
Activations Density 0.184%