INDEX
Explanations
discussions comparing narrative focus or thematic changes in storytelling
New Auto-Interp
Negative Logits
my
-0.16
indeed
-0.14
simply
-0.14
may
-0.14
should
-0.14
ë¿IJ
-0.13
cannot
-0.13
truly
-0.13
ama
-0.13
simple
-0.13
POSITIVE LOGITS
yourselves
0.32
yourself
0.31
youre
0.24
ä½łçļĦ
0.23
your
0.23
your
0.22
Yourself
0.21
)?↵
0.20
ä½ł
0.19
ï¼Ł↵
0.19
Activations Density 0.279%