INDEX
Explanations
proper nouns, specifically names like "Brian."
the name "Brian."
New Auto-Interp
Negative Logits
roxy
-0.85
pir
-0.79
uph
-0.78
ãĥ´ãĤ¡
-0.77
UV
-0.75
lower
-0.69
VOL
-0.68
ugal
-0.67
TOR
-0.67
pter
-0.67
POSITIVE LOGITS
Patrick
0.85
Matthews
0.82
Tomas
0.82
Moy
0.80
Terry
0.80
Greene
0.79
Reed
0.78
Brian
0.78
Gardner
0.78
Tiff
0.76
Activations Density 0.007%