INDEX
Explanations
quantities and comparisons involving size or duration
New Auto-Interp
Negative Logits
abetes
-0.65
HideFlags
-0.60
uitable
-0.56
__':
-0.53
PreInfinity
-0.51
pañas
-0.49
깥
-0.49
__':
-0.49
auré
-0.48
Roskov
-0.48
POSITIVE LOGITS
sized
1.23
sounding
1.18
looking
1.14
priced
1.13
shaped
0.98
smelling
0.97
LOOKING
0.97
minded
0.95
looking
0.95
valued
0.92
Activations Density 0.704%