INDEX
Explanations
words related to storytelling and narratives
references to narratives and storytelling
New Auto-Interp
Negative Logits
ertodd
-0.93
abad
-0.86
ikarp
-0.86
enhagen
-0.85
eni
-0.83
IER
-0.83
unte
-0.80
cot
-0.78
shine
-0.78
por
-0.78
POSITIVE LOGITS
disson
0.99
narratives
0.96
narrative
0.91
linking
0.90
framing
0.89
depiction
0.88
portrayal
0.88
portray
0.87
depicting
0.85
portraying
0.85
Activations Density 0.077%