INDEX
Explanations
the word "charity."
New Auto-Interp
Negative Logits
<bos>
-0.99
in
-0.68
,
-0.68
not
-0.66
a
-0.65
for
-0.64
to
-0.60
the
-0.59
on
-0.56
just
-0.56
POSITIVE LOGITS
]))
0.90
?")
0.85
)$}
0.82
Theſe
0.81
--$
0.81
StoryboardSegue
0.80
"])
0.79
"'");
0.78
)،
0.78
)".
0.76
Activations Density 1.288%