INDEX
Explanations
actions involving movement or physical interaction
New Auto-Interp
Negative Logits
uhan
-0.15
coop
-0.15
indle
-0.15
cum
-0.15
ERA
-0.14
èĨ
-0.14
ضÙħ
-0.14
erah
-0.14
ällt
-0.14
ä¸Ģ页
-0.14
POSITIVE LOGITS
around
0.44
around
0.40
autour
0.36
Around
0.35
Around
0.33
-around
0.33
вокÑĢÑĥг
0.28
kolem
0.24
everywhere
0.22
movements
0.21
Activations Density 0.142%