INDEX
Explanations
official statements or declarations
instances of the word "officially" in various contexts
New Auto-Interp
Negative Logits
ĸļ
-0.79
rug
-0.79
wich
-0.75
lihood
-0.74
Emin
-0.73
ocene
-0.71
liest
-0.70
ritch
-0.69
onal
-0.69
vich
-0.67
POSITIVE LOGITS
sanctioned
0.83
cleared
0.83
disbanded
0.81
officially
0.81
speaking
0.78
separated
0.76
declared
0.75
induct
0.74
dom
0.74
formulated
0.73
Activations Density 0.010%