INDEX
Explanations
the word "this" in various contexts
this followed by is
New Auto-Interp
Negative Logits
autorytatywna
-1.05
snippetHide
-0.96
Италијани
-0.91
<unused74>
-0.89
<unused52>
-0.89
<unused23>
-0.89
<unused8>
-0.89
<unused14>
-0.89
<unused3>
-0.89
[@BOS@]
-0.89
POSITIVE LOGITS
this
0.72
THIS
0.40
is
0.37
This
0.36
is
0.36
'
0.36
which
0.34
th
0.34
THIS
0.34
it
0.33
Activations Density 0.028%