INDEX
Explanations
the word "out"
instances of the phrase "go out."
New Auto-Interp
Negative Logits
Dys
-0.66
iol
-0.63
ulous
-0.63
hiba
-0.62
Primordial
-0.60
gemony
-0.60
cius
-0.60
benef
-0.60
ajor
-0.58
DT
-0.58
POSITIVE LOGITS
fitted
1.01
casts
0.87
doors
0.83
ranged
0.83
stretched
0.82
ta
0.80
wards
0.80
partying
0.80
door
0.80
shopping
0.77
Activations Density 0.049%