INDEX
Explanations
numerical data such as measurements and quantities
numerical values and statistics related to natural disasters or significant events
New Auto-Interp
Negative Logits
Ide
-0.81
terms
-0.67
actionDate
-0.66
isoft
-0.64
abeth
-0.63
imaru
-0.62
preferences
-0.61
ashtra
-0.61
forth
-0.60
ide
-0.60
POSITIVE LOGITS
feet
1.30
inches
1.27
mph
1.25
metre
1.24
centimeters
1.21
meters
1.18
foot
1.17
cubic
1.17
meter
1.17
mph
1.16
Activations Density 0.174%