INDEX
Explanations
mentions of artists, particularly those involved in music and film
New Auto-Interp
Negative Logits
/doc
-0.15
_DS
-0.15
kyt
-0.15
fra
-0.14
HEET
-0.14
okt
-0.14
ượt
-0.14
oku
-0.14
Independent
-0.14
lish
-0.14
POSITIVE LOGITS
Mas
0.28
Minor
0.26
Hide
0.24
Hi
0.23
Hide
0.23
Mas
0.22
Kaz
0.22
Nob
0.21
ÐľÐ°Ñģ
0.20
Sets
0.20
Activations Density 0.032%