INDEX
Explanations
mentions of influential figures in technology and finance
New Auto-Interp
Negative Logits
selection
-0.76
Ukrain
-0.65
conflicting
-0.65
repression
-0.64
rique
-0.64
Mistress
-0.61
Heb
-0.61
Rite
-0.60
batters
-0.60
wives
-0.60
POSITIVE LOGITS
Zuckerberg
0.92
Labs
0.83
heimer
0.81
Jinping
0.81
frey
0.80
zee
0.77
Founder
0.75
Jr
0.75
hetti
0.74
ervative
0.74
Activations Density 0.011%