INDEX
Explanations
the presence of the syllable "qu."
New Auto-Interp
Negative Logits
i
-0.26
an
-0.25
ant
-0.20
arters
-0.19
antasy
-0.17
anou
-0.17
alah
-0.17
anik
-0.17
ãĥ£
-0.16
ot
-0.16
POSITIVE LOGITS
aña
0.20
añ
0.16
MBOL
0.16
ice
0.16
OTO
0.15
hart
0.15
αÏĤ
0.15
enk
0.15
ison
0.15
vnÃŃ
0.15
Activations Density 0.071%