INDEX
Explanations
references to movement and transport actions
New Auto-Interp
Negative Logits
ÐĿаÑģ
-0.16
atel
-0.14
éľĩ
-0.14
wing
-0.14
ithe
-0.14
rep
-0.14
égor
-0.14
prs
-0.14
oton
-0.13
rep
-0.13
POSITIVE LOGITS
ogan
0.17
ewe
0.16
llib
0.15
into
0.15
Ðļоли
0.15
ÅĻeh
0.15
registers
0.15
hores
0.14
inja
0.14
eyi
0.14
Activations Density 0.208%