INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
as
1.05
ok
0.99
ie
0.96
at
0.95
oc
0.91
id
0.85
or
0.84
il
0.83
in
0.79
he
0.79
POSITIVE LOGITS
ките
0.86
estão
0.83
tránsito
0.82
ءَ
0.81
ꯕ
0.80
serão
0.79
inclu
0.79
Publ
0.78
Entrada
0.78
ḩ
0.78
Activations Density 0.000%