INDEX
Explanations
mentions of political figures, specifically the name "Sarkozy" and variations thereof
mentions of specific individuals, particularly political figures
New Auto-Interp
Negative Logits
âĸ¬âĸ¬
-0.73
66666666
-0.70
ãĥĩãĤ£
-0.69
tered
-0.68
bered
-0.68
LEASE
-0.67
oration
-0.66
DERR
-0.66
ters
-0.65
Universal
-0.64
POSITIVE LOGITS
ozy
1.27
Sark
0.97
indal
0.93
perm
0.80
daq
0.79
olini
0.79
inia
0.79
esian
0.79
edIn
0.77
aran
0.76
Activations Density 0.020%