INDEX
Explanations
elements that discuss storytelling and narrative structure
New Auto-Interp
Negative Logits
ery
-0.23
/bus
-0.16
ï¸ı
-0.15
----</
-0.15
TION
-0.15
ders
-0.15
alf
-0.15
ullen
-0.15
ick
-0.15
sy
-0.15
POSITIVE LOGITS
/story
0.20
arc
0.18
-driven
0.17
told
0.17
ative
0.17
/Instruction
0.16
atively
0.16
structure
0.16
arcs
0.16
_voice
0.15
Activations Density 0.010%