INDEX
Explanations
lines of code or text that are part of a software program
New Auto-Interp
Negative Logits
myſelf
-1.84
Monfieur
-1.78
ſtate
-1.72
Efq
-1.72
Jefus
-1.67
Majefty
-1.63
itſelf
-1.62
purpoſe
-1.62
ſeveral
-1.61
Chriftian
-1.57
POSITIVE LOGITS
ta
0.85
ber
0.84
de
0.83
po
0.83
di
0.77
le
0.76
har
0.74
ri
0.74
ab
0.73
da
0.73
Activations Density 0.428%