INDEX
Explanations
mentions of a specific name, "Hart."
mentions of the name "Hart."
New Auto-Interp
Negative Logits
ntil
-0.89
terday
-0.87
srf
-0.77
avorite
-0.69
ournal
-0.69
CLASSIFIED
-0.68
millenn
-0.65
occas
-0.64
imposition
-0.62
PDATE
-0.62
POSITIVE LOGITS
mut
1.17
wig
1.12
mann
1.10
nell
1.01
enstein
1.00
igan
0.99
lich
0.96
wick
0.96
master
0.94
lett
0.91
Activations Density 0.011%