INDEX
Explanations
phrases related to power or authority
the phrase "the power of" in various contexts
New Auto-Interp
Negative Logits
bats
-0.75
hao
-0.74
externalToEVAOnly
-0.73
çĦ
-0.72
jee
-0.72
wic
-0.72
wcsstore
-0.68
bus
-0.67
fml
-0.67
lict
-0.66
POSITIVE LOGITS
persuasion
0.97
intimidation
0.95
imagination
0.85
compulsion
0.77
intuition
0.76
amplification
0.76
storytelling
0.75
influence
0.74
inference
0.72
darkness
0.70
Activations Density 0.090%