INDEX
Explanations
proper nouns of individuals
mentions of specific individuals, particularly those with the surname 'Robertson'
New Auto-Interp
Negative Logits
ymes
-0.72
udic
-0.69
ERE
-0.67
ures
-0.67
Romantic
-0.66
UME
-0.66
ARE
-0.65
usp
-0.64
abetes
-0.63
recy
-0.63
POSITIVE LOGITS
kinson
0.91
iets
0.89
oute
0.87
yssey
0.86
Robertson
0.86
igon
0.81
onite
0.80
Broadcasting
0.77
sey
0.77
nikov
0.72
Activations Density 0.021%