INDEX
Explanations
proper names, specifically the name "Patrick."
New Auto-Interp
Negative Logits
TOR
-0.77
ð
-0.64
nexus
-0.64
agency
-0.61
htar
-0.61
zx
-0.61
iewicz
-0.61
glers
-0.61
schild
-0.61
plug
-0.60
POSITIVE LOGITS
Leah
0.92
Patrick
0.82
Reilly
0.81
Byrne
0.81
Duffy
0.80
Patterson
0.79
Murphy
0.79
Kane
0.78
Roth
0.78
Buchanan
0.77
Activations Density 0.011%