INDEX
Explanations
just statements or casual conversation
New Auto-Interp
Negative Logits
just
1.09
just
1.01
Just
0.99
Just
0.98
JUST
0.92
vừa
0.74
upravo
0.73
JUST
0.70
justo
0.69
právě
0.68
POSITIVE LOGITS
ifiably
1.15
plain
0.84
plain
0.61
IFIED
0.57
ifiable
0.57
ification
0.57
ified
0.56
FYI
0.54
Plain
0.54
单纯
0.52
Activations Density 0.125%