INDEX
Explanations
references to personal experiences and storytelling
New Auto-Interp
Negative Logits
now
-0.19
anymore
-0.18
until
-0.18
throughout
-0.17
tomorrow
-0.16
until
-0.16
since
-0.15
缮åīį
-0.15
and
-0.15
anything
-0.14
POSITIVE LOGITS
someone
0.27
someone
0.27
somebody
0.27
æŁIJ
0.23
çļĦä¸Ģ个
0.22
_while
0.20
Someone
0.20
whilst
0.19
alguien
0.19
eines
0.18
Activations Density 0.553%