INDEX
Explanations
mentions of a specific person named Manuel
names of individuals, particularly those of prominent people
New Auto-Interp
Negative Logits
nces
-1.01
ngth
-0.81
ritic
-0.80
orks
-0.80
ulhu
-0.74
ramid
-0.73
earchers
-0.73
reen
-0.73
AKING
-0.72
rawl
-0.71
POSITIVE LOGITS
Manuel
1.02
theless
0.88
Antonio
0.87
ique
0.82
Guer
0.80
ican
0.77
Gutierrez
0.77
Berger
0.76
Gomez
0.73
Santos
0.73
Activations Density 0.013%