INDEX
Explanations
phrases indicating duration or length
New Auto-Interp
Negative Logits
iesel
-0.18
AFX
-0.15
msp
-0.15
arty
-0.14
ibri
-0.14
_('-0.14
anela
-0.14
æľĭ
-0.14
oder
-0.14
ington
-0.14
POSITIVE LOGITS
ass
0.17
ãĥ©ãĥĥãĤ¯
0.17
ast
0.16
Ïĥο
0.15
Axe
0.15
there
0.14
baum
0.14
оÑģ
0.14
zia
0.14
asta
0.13
Activations Density 0.008%