INDEX
Explanations
instances where the word "had" is used with an emphasis or importance
instances of the word "had."
New Auto-Interp
Negative Logits
auto
-0.67
automatic
-0.63
cookie
-0.63
envelope
-0.63
appearance
-0.62
shape
-0.62
imp
-0.60
outward
-0.60
ens
-0.59
enc
-0.59
POSITIVE LOGITS
had
4.24
has
1.83
Had
1.78
was
1.62
didn
1.56
were
1.51
did
1.39
ha
1.35
hid
1.34
Had
1.34
Activations Density 0.013%