INDEX
Explanations
phrases related to vaccination status and awareness
New Auto-Interp
Negative Logits
ñas
-0.17
hibit
-0.15
mach
-0.15
gia
-0.14
antan
-0.14
EXCEPTION
-0.14
vale
-0.14
istrovstvÃŃ
-0.13
ÑĪÑĤÑĥ
-0.13
ær
-0.13
POSITIVE LOGITS
iler
0.17
è¾°
0.17
oly
0.16
lyn
0.15
ervo
0.14
_dummy
0.14
ILER
0.14
леж
0.14
Grü
0.14
WX
0.14
Activations Density 0.219%