INDEX
Explanations
occurrences of the word "have" in various forms
New Auto-Interp
Negative Logits
myſelf
-1.17
itſelf
-1.15
themſelves
-0.99
himſelf
-0.98
Monfieur
-0.97
ainfi
-0.97
becauſe
-0.95
-0.95
ſtate
-0.95
againſt
-0.91
POSITIVE LOGITS
had
1.30
a
1.18
have
1.10
has
1.08
had
1.03
an
1.02
HAD
0.99
have
0.99
Had
0.97
Have
0.96
Activations Density 0.431%