INDEX
Explanations
parts of speech related to the present tense
New Auto-Interp
Negative Logits
uſed
-0.97
raiſ
-0.87
themſelves
-0.86
itſelf
-0.84
myſelf
-0.84
Theſe
-0.81
iſt
-0.80
diſt
-0.79
ſou
-0.78
ſec
-0.77
POSITIVE LOGITS
and
0.65
amp
0.63
&
0.61
and
0.59
\&
0.59
&
0.58
и
0.57
AND
0.57
And
0.56
AND
0.54
Activations Density 0.039%