INDEX
Explanations
the preposition "of" and its different contexts in a text
New Auto-Interp
Negative Logits
ä¸ĢçĤ¹
-0.17
ä¸Ģå¹´
-0.15
ula
-0.15
.Accessible
-0.15
agina
-0.15
headed
-0.15
ogy
-0.14
remen
-0.14
/code
-0.14
acher
-0.14
POSITIVE LOGITS
/from
0.16
صر
0.14
illard
0.14
/all
0.14
our
0.14
ean
0.14
uji
0.14
instein
0.13
udd
0.13
InThe
0.13
Activations Density 0.181%