INDEX
Explanations
references to annual events, specifically competitions and festivals
New Auto-Interp
Negative Logits
BTN
-0.15
uya
-0.15
utar
-0.14
Ting
-0.14
ritel
-0.14
afen
-0.14
erty
-0.14
Corn
-0.14
Polo
-0.14
eller
-0.13
POSITIVE LOGITS
Guild
0.16
349
0.15
akter
0.15
yasal
0.14
ovali
0.14
pas
0.14
ìłľ
0.14
[--
0.14
rray
0.14
rové
0.13
Activations Density 0.023%