INDEX
Explanations
occurrences of the name "Simon" in the text
New Auto-Interp
Negative Logits
inea
-0.15
uye
-0.15
suite
-0.15
LAN
-0.15
Ïħ
-0.14
ourcem
-0.14
Zoom
-0.14
elah
-0.14
auc
-0.14
leftJoin
-0.14
POSITIVE LOGITS
etta
0.31
etti
0.25
elli
0.18
neau
0.18
pj
0.17
ett
0.17
Gallup
0.16
Templ
0.16
etty
0.16
iac
0.16
Activations Density 0.005%