INDEX
Explanations
mentions of leaders or leadership roles
occurrences of the word "leader"
New Auto-Interp
Negative Logits
enegger
-0.73
Pwr
-0.72
Neighbor
-0.71
ALLY
-0.64
ITNESS
-0.63
Ukrain
-0.62
agra
-0.62
tan
-0.61
Fusion
-0.60
urses
-0.59
POSITIVE LOGITS
boards
1.29
board
1.12
doms
1.09
aroo
0.91
leader
0.89
hip
0.88
hips
0.88
esses
0.87
pieces
0.86
pins
0.85
Activations Density 0.053%