INDEX
Explanations
digits followed by a period
New Auto-Interp
Negative Logits
驒
0.58
きゃ
0.57
bral
0.56
кистон
0.55
ᅣ
0.54
ಂತೆ
0.52
imaginable
0.52
outcry
0.52
icità
0.51
грева
0.51
POSITIVE LOGITS
.
1.08
.:
0.86
.`
0.82
.-
0.79
./
0.78
.%
0.76
.?
0.75
.)
0.75
.,
0.74
.';
0.74
Activations Density 0.582%