INDEX
Explanations
monetary values and related symbols
New Auto-Interp
Negative Logits
esterno
-0.72
Signalez
-0.72
Efq
-0.71
houſe
-0.69
firſt
-0.68
ſelf
-0.66
himſelf
-0.66
itſelf
-0.64
myſelf
-0.64
uſed
-0.63
POSITIVE LOGITS
ndash
0.80
other
0.73
whatnot
0.71
amp
0.69
0.69
subsequent
0.66
others
0.66
rogens
0.66
それに
0.64
﹠
0.64
Activations Density 0.681%