INDEX
Explanations
the word "ordinary" appearing in text
instances of the word "ordinary."
New Auto-Interp
Negative Logits
haw
-0.70
olic
-0.68
arth
-0.67
lez
-0.66
AIDS
-0.65
asus
-0.65
alez
-0.64
Recomm
-0.63
rogram
-0.63
oran
-0.61
POSITIVE LOGITS
ordinary
1.12
ordinary
0.95
mortals
0.92
isation
0.83
sized
0.81
ised
0.79
cy
0.77
everyday
0.77
weekday
0.77
isable
0.75
Activations Density 0.010%