INDEX
Explanations
words related to design and composition processes
New Auto-Interp
Negative Logits
<eos>
-0.64
it
-0.56
not
-0.54
ter
-0.52
now
-0.51
-
-0.49
per
-0.47
can
-0.46
its
-0.46
><!--
-0.46
POSITIVE LOGITS
myſelf
1.34
itſelf
1.22
becauſe
1.19
Monfieur
1.18
―――――
1.16
Theſe
1.14
Anſ
1.12
ſmall
1.12
Efq
1.11
againſt
1.11
Activations Density 0.403%