INDEX
Explanations
words related to art and culture, particularly names and terms associated with artistic events
New Auto-Interp
Negative Logits
es
-0.28
y
-0.28
ed
-0.26
em
-0.24
e
-0.24
esi
-0.21
esy
-0.21
etti
-0.20
ex
-0.20
yg
-0.20
POSITIVE LOGITS
lectual
0.29
icious
0.29
los
0.25
izabeth
0.25
ty
0.22
lic
0.22
éfono
0.21
logen
0.21
ldata
0.21
inux
0.20
Activations Density 0.140%