INDEX
Explanations
the name "Lewandowski"
mentions of the name "Lew"
New Auto-Interp
Negative Logits
ACTED
-0.91
à¨
-0.77
vain
-0.73
OPLE
-0.73
senal
-0.69
اÙĦ
-0.69
CHR
-0.67
ĸļ
-0.67
thood
-0.66
expr
-0.66
POSITIVE LOGITS
andowski
1.33
Lew
1.02
insky
0.98
erk
0.90
enstein
0.88
ington
0.87
Lew
0.87
etz
0.85
sey
0.84
itsch
0.83
Activations Density 0.008%