INDEX
Explanations
legal documents and regulations
New Auto-Interp
Negative Logits
-
0.80
o
0.65
\
0.63
jika
0.59
karena
0.58
ketika
0.57
kombin
0.55
l
0.55
t
0.54
}
0.52
POSITIVE LOGITS
P
0.79
З
0.76
H
0.74
F
0.73
B
0.70
T
0.70
Ф
0.68
W
0.67
ZV
0.66
Gestion
0.64
Activations Density 0.066%