INDEX
Explanations
people's names or entities related to them
names and terms related to persons involved in leadership or formal organizations
New Auto-Interp
Negative Logits
chat
-0.91
Ec
-0.74
Tablet
-0.73
Panel
-0.72
Borough
-0.71
panel
-0.69
Counter
-0.69
Bul
-0.68
ãĤ±
-0.68
Alban
-0.66
POSITIVE LOGITS
heed
1.78
mer
1.49
corps
1.44
coli
1.30
Lilly
1.24
Caldwell
1.17
fir
1.16
Avery
1.09
isf
0.98
ANGEL
0.98
Activations Density 0.032%