INDEX
Explanations
associations with actions indicating engagement or involvement in situations
New Auto-Interp
Negative Logits
671
-0.15
oco
-0.15
hữu
-0.14
Kỳ
-0.14
iele
-0.14
pivot
-0.13
ISTA
-0.13
ITA
-0.13
ạng
-0.13
gal
-0.13
POSITIVE LOGITS
etz
0.17
inton
0.17
nia
0.15
egan
0.15
wap
0.15
Ñĥж
0.14
ем
0.14
upa
0.14
releg
0.14
dispatch
0.14
Activations Density 0.010%