INDEX
Explanations
references to new beginnings or introductions in various contexts, particularly in relation to debut performances or albums
New Auto-Interp
Negative Logits
352
-0.18
414
-0.16
erness
-0.15
CRET
-0.15
wang
-0.14
anker
-0.14
Diego
-0.14
ospace
-0.14
rones
-0.14
alan
-0.14
POSITIVE LOGITS
/original
0.17
ante
0.16
ahn
0.16
šk
0.16
/start
0.15
chez
0.15
ductory
0.14
multiline
0.14
Moy
0.14
atal
0.14
Activations Density 0.021%