INDEX
Explanations
phrases containing the term "so-called."
phrases that include the term "so-called."
New Auto-Interp
Negative Logits
furthermore
-0.80
then
-0.70
indeed
-0.69
nevertheless
-0.69
moreover
-0.67
ande
-0.66
certainly
-0.63
!.
-0.63
SPONSORED
-0.62
also
-0.62
POSITIVE LOGITS
"
1.15
"#
1.10
'
1.00
"'
0.96
"+
0.89
"@
0.84
"-
0.81
``
0.79
"\
0.79
''
0.78
Activations Density 0.081%