INDEX
Negative Logits
an
-0.09
])↵↵
-0.09
notably
-0.08
a
-0.08
some
-0.08
gye
-0.08
"])↵↵
-0.08
your
-0.08
jà
-0.08
ônia
-0.07
POSITIVE LOGITS
Additionally
0.09
、この
0.09
hierdoor
0.08
、大
0.08
않을
0.08
ETING
0.08
Sometimes
0.08
otras
0.08
లేదా
0.08
This
0.08
Activations Density 0.129%