INDEX
Explanations
words related to bravery or courage
references to courage and bravery
New Auto-Interp
Negative Logits
eor
-0.92
enfranch
-0.74
payer
-0.73
washer
-0.71
ramid
-0.69
mers
-0.67
effects
-0.66
program
-0.66
iverse
-0.65
cise
-0.63
POSITIVE LOGITS
ously
1.40
courage
1.05
bravery
0.89
courageous
0.87
ous
0.87
Courage
0.82
inspiring
0.79
faced
0.78
heroism
0.77
士
0.76
Activations Density 0.054%