INDEX
Explanations
texts mentioning a person named Brian
mentions of the name "Brian."
New Auto-Interp
Negative Logits
roxy
-0.88
ãĥ´ãĤ¡
-0.72
UV
-0.71
TOR
-0.70
pmwiki
-0.69
pir
-0.68
ylum
-0.67
Pradesh
-0.67
icted
-0.65
uph
-0.64
POSITIVE LOGITS
Moy
0.83
Becker
0.81
Cage
0.79
Blessed
0.78
Greene
0.77
Wright
0.76
Herbert
0.76
Patrick
0.76
Ross
0.75
Bah
0.74
Activations Density 0.015%