INDEX
Explanations
articles and determiners in the text
New Auto-Interp
Negative Logits
Mahomet
-1.03
Phry
-0.97
Pyrr
-0.96
Shakspeare
-0.92
Sopho
-0.92
Euphrates
-0.88
Athenians
-0.87
itſelf
-0.86
myſelf
-0.85
Aene
-0.83
POSITIVE LOGITS
the
1.10
el
0.94
Το
0.89
THE
0.89
The
0.88
le
0.88
El
0.87
Le
0.87
la
0.87
del
0.84
Activations Density 0.026%