INDEX
Explanations
names of notable individuals and brands
New Auto-Interp
Negative Logits
itſelf
-1.57
^(@)
-1.40
myſelf
-1.34
Monfieur
-1.30
iſt
-1.28
Jefus
-1.27
themſelves
-1.26
ainfi
-1.25
CreateTagHelper
-1.24
auffi
-1.24
POSITIVE LOGITS
0.76
'
0.72
↵
0.70
-
0.68
.
0.66
&
0.66
<eos>
0.64
I
0.64
to
0.63
’
0.63
Activations Density 0.523%