INDEX
Explanations
names of people and institutions
prominent names or titles associated with authority figures
New Auto-Interp
Negative Logits
clubhouse
-0.66
ModLoader
-0.59
Millennials
-0.58
millennials
-0.58
Presidents
-0.57
envy
-0.55
subsistence
-0.55
LEASE
-0.55
enemies
-0.55
presumptive
-0.55
POSITIVE LOGITS
ijn
0.92
(@
0.92
ansky
0.88
atz
0.88
inski
0.88
itz
0.88
gaard
0.87
enz
0.85
ofer
0.85
iak
0.84
Activations Density 0.554%