INDEX
Explanations
the word "Hampton" and its variations within the text
New Auto-Interp
Negative Logits
educ
-0.16
ents
-0.16
èŤ
-0.15
479
-0.15
444
-0.15
inx
-0.14
_listen
-0.14
omanip
-0.14
697
-0.14
own
-0.14
POSITIVE LOGITS
ilton
0.29
ham
0.26
pered
0.25
Ham
0.23
mond
0.21
pton
0.20
Ham
0.20
Hamm
0.20
.ham
0.19
ham
0.18
Activations Density 0.013%