INDEX
Explanations
occurrences of specific verbs and their inflections in various contexts
New Auto-Interp
Negative Logits
meer
-0.17
enis
-0.16
arsi
-0.16
prav
-0.15
chod
-0.15
riter
-0.15
gorithm
-0.14
èĻ
-0.14
scl
-0.14
akis
-0.14
POSITIVE LOGITS
onto
0.17
into
0.17
onto
0.16
/embed
0.16
DIM
0.15
into
0.15
ÑģÑİ
0.15
รà¸ģ
0.15
lig
0.14
DIC
0.14
Activations Density 0.079%