INDEX
Explanations
mentions of the name "Lawrence"
mentions of the name "Lawrence."
New Auto-Interp
Negative Logits
izoph
-0.87
raid
-0.86
ramid
-0.85
resso
-0.84
hedral
-0.79
joined
-0.79
tnc
-0.79
arers
-0.78
cffff
-0.75
graded
-0.72
POSITIVE LOGITS
Liver
1.01
Lawrence
0.94
ville
0.88
Berkeley
0.85
rence
0.81
Wel
0.80
Hague
0.80
Kra
0.77
Foster
0.77
Anderson
0.77
Activations Density 0.016%