INDEX
Explanations
events related to mouse interactions
New Auto-Interp
Negative Logits
esson
-0.79
rating
-0.76
orian
-0.75
ibel
-0.72
Buffy
-0.72
iever
-0.72
eous
-0.71
ieves
-0.71
ivism
-0.70
namese
-0.70
POSITIVE LOGITS
cursor
1.00
pointer
0.99
cules
0.90
pad
0.88
Mouse
0.85
pox
0.83
mice
0.81
wheel
0.79
cule
0.79
mouse
0.78
Activations Density 0.022%