INDEX
Explanations
punctuation marks and sentence endings
New Auto-Interp
Negative Logits
Upgrade
-0.71
bon
-0.66
vitt
-0.64
ESTY
-0.63
dillo
-0.62
waitKey
-0.62
}{*}{}-0.61
f
-0.60
separate
-0.60
ocarp
-0.59
POSITIVE LOGITS
ainfi
0.84
"><?=
0.81
Kaly
0.80
shewn
0.79
tiroirs
0.77
feroit
0.75
ſta
0.74
,.
0.73
larmes
0.73
þat
0.73
Activations Density 0.517%