INDEX
Explanations
functionality and attributes
New Auto-Interp
Negative Logits
fossero
0.16
sollen
0.16
бъдат
0.15
."
0.15
aient
0.15
fueran
0.14
seien
0.14
".
0.14
'.
0.14
soient
0.14
POSITIVE LOGITS
provides
0.30
operates
0.27
requires
0.26
serves
0.26
itself
0.25
обладает
0.25
sits
0.25
possesses
0.25
has
0.25
имеет
0.25
Activations Density 0.713%