INDEX
Explanations
references to K-pop groups and related cultural phenomena
New Auto-Interp
Negative Logits
berger
-0.19
udson
-0.15
stin
-0.15
orex
-0.15
ÑĢазд
-0.15
abra
-0.15
asher
-0.14
(TM
-0.14
ango
-0.14
inds
-0.14
POSITIVE LOGITS
BTS
0.26
TXT
0.23
Jung
0.21
ARM
0.21
Rap
0.20
boy
0.20
RM
0.20
boys
0.19
éĺ²
0.18
Pentagon
0.17
Activations Density 0.013%