INDEX
Explanations
occurrences of the name 'Alex'
references to the name "Alex"
New Auto-Interp
Negative Logits
merce
-0.77
office
-0.72
liness
-0.68
stakes
-0.67
enegger
-0.66
unsub
-0.65
recy
-0.65
ttes
-0.65
unity
-0.63
primary
-0.63
POSITIVE LOGITS
iev
0.88
iol
0.85
ei
0.81
inia
0.78
orean
0.77
Haley
0.76
rons
0.76
Koz
0.76
iants
0.75
osta
0.74
Activations Density 0.013%