INDEX
Explanations
mentions of the name "Robson."
the occurrence of the word "son"
New Auto-Interp
Negative Logits
heels
-0.68
deficits
-0.66
spread
-0.63
neut
-0.62
odies
-0.62
ptions
-0.62
breaches
-0.60
arded
-0.60
uters
-0.59
ANN
-0.58
POSITIVE LOGITS
nen
0.88
strom
0.86
nets
0.80
ville
0.79
Jr
0.78
hood
0.78
oran
0.77
ics
0.77
gaard
0.76
son
0.75
Activations Density 0.020%