INDEX
Explanations
forms of the verb "to be."
New Auto-Interp
Negative Logits
तर
-0.14
podob
-0.14
yourselves
-0.13
mouseleave
-0.13
izia
-0.13
noen
-0.13
cour
-0.13
:]
-0.12
atten
-0.12
porr
-0.12
POSITIVE LOGITS
the
0.30
king
0.29
our
0.26
where
0.26
THE
0.24
King
0.24
their
0.23
KING
0.22
responsible
0.20
primary
0.20
Activations Density 0.410%