INDEX
Explanations
conjunctions and words indicating contrast or opposition
New Auto-Interp
Negative Logits
tvguidetime
-0.92
―――――
-0.86
Zwar
-0.86
SizeF
-0.84
AndEndTag
-0.83
photolibrary
-0.82
otomatig
-0.82
myſelf
-0.80
Anſ
-0.80
*/;
-0.79
POSITIVE LOGITS
it
0.97
there
0.89
I
0.80
the
0.77
they
0.76
we
0.74
these
0.71
It
0.69
you
0.69
this
0.68
Activations Density 0.123%