INDEX
Explanations
instances of the word "had" as a significant term in the text
New Auto-Interp
Negative Logits
Olsson
-0.96
Reuter
-0.83
Torrey
-0.82
LLocation
-0.81
Guen
-0.81
Dickinson
-0.80
SLS
-0.80
Hutchins
-0.80
Rek
-0.79
Bask
-0.78
POSITIVE LOGITS
Had
1.59
had
1.54
Had
1.51
HAD
1.49
had
1.32
HAD
1.07
hadn
0.96
hatten
0.96
avaient
0.94
hatte
0.94
Activations Density 0.104%