INDEX
Explanations
instances of the verb "are" and related conjugations
New Auto-Interp
Negative Logits
rif
-0.16
ое
-0.15
richt
-0.15
Scalars
-0.15
mith
-0.14
itaire
-0.14
iÄĩ
-0.14
ìĹ
-0.14
rocket
-0.14
reli
-0.14
POSITIVE LOGITS
ns
0.26
nda
0.21
ngo
0.20
ospace
0.18
ncia
0.18
nger
0.18
tsky
0.18
ncy
0.18
nder
0.18
ments
0.17
Activations Density 0.039%