INDEX
Explanations
recent and ongoing activities
New Auto-Interp
Negative Logits
one
0.35
Gaussian
0.35
you
0.34
ER
0.34
details
0.34
agad
0.33
d
0.32
that
0.32
RENCY
0.32
ونی
0.31
POSITIVE LOGITS
lately
0.79
recientemente
0.69
منذ
0.66
Lately
0.64
recentemente
0.63
since
0.63
récemment
0.63
sejak
0.62
been
0.61
近年
0.60
Activations Density 0.100%