INDEX
Negative Logits
I
0.49
،
0.45
5
0.45
6
0.44
).
0.44
gu
0.43
gga
0.42
8
0.42
ga
0.42
”،
0.41
POSITIVE LOGITS
0.56
to
0.52
on
0.51
of
0.50
one
0.50
The
0.49
is
0.46
the
0.46
ana
0.46
as
0.45
Activations Density 0.068%
I
،
5
6
).
gu
gga
8
ga
”،
to
on
of
one
The
is
the
ana
as