INDEX
Explanations
mentions of time
references to the concept of time
New Auto-Interp
Negative Logits
olor
-0.71
DNA
-0.66
products
-0.65
ives
-0.64
uber
-0.62
Noir
-0.62
uffy
-0.62
comments
-0.61
beginnings
-0.60
atl
-0.60
POSITIVE LOGITS
around
1.47
round
1.30
Around
1.13
around
1.05
round
0.91
frame
0.86
rounder
0.86
Round
0.78
Around
0.78
period
0.74
Activations Density 0.077%