INDEX
Explanations
words related to ownership or possession
New Auto-Interp
Negative Logits
crossorigin
-0.16
ering
-0.16
amp
-0.16
tat
-0.15
alls
-0.15
ä¸įåΰ
-0.15
teenth
-0.15
-0.15
lah
-0.14
contres
-0.14
POSITIVE LOGITS
irez
0.15
ož
0.15
Bare
0.14
alim
0.14
través
0.14
OUN
0.14
ichen
0.14
anas
0.14
erk
0.13
ibal
0.13
Activations Density 0.031%