INDEX
Explanations
mentions of the name "Lawrence"
references to the name "Lawrence."
New Auto-Interp
Negative Logits
resso
-0.88
izoph
-0.86
joined
-0.85
ramid
-0.85
requ
-0.80
tnc
-0.79
arers
-0.76
raid
-0.74
visor
-0.74
worldly
-0.73
POSITIVE LOGITS
Lawrence
1.07
Liver
1.05
ville
0.90
rence
0.86
Berkeley
0.84
Foster
0.80
Hague
0.79
Wel
0.77
Anderson
0.77
Feldman
0.77
Activations Density 0.013%