INDEX
Explanations
specific articles and determiners in sentences
New Auto-Interp
Negative Logits
ãĢij
-0.16
oku
-0.15
adow
-0.15
illo
-0.14
ικο
-0.14
нев
-0.14
deki
-0.14
ÏĢη
-0.14
othy
-0.14
odore
-0.14
POSITIVE LOGITS
lot
0.18
little
0.16
few
0.16
LOT
0.15
Certain
0.15
certain
0.15
BindingUtil
0.15
hd
0.14
iid
0.14
áÄį
0.14
Activations Density 0.213%