INDEX
Explanations
mentions of locations or individuals with the name "Son"
mentions of "Sonoma."
New Auto-Interp
Negative Logits
erences
-0.74
kefeller
-0.71
GROUND
-0.61
Duff
-0.60
DERR
-0.59
jamin
-0.57
digest
-0.57
iculty
-0.56
ORD
-0.56
``(
-0.56
POSITIVE LOGITS
nets
1.18
ghai
1.00
ata
0.98
oma
0.97
ority
0.97
ja
0.89
heses
0.88
orus
0.87
osphere
0.86
hesis
0.85
Activations Density 0.021%