INDEX
Explanations
instances of character development and emotional responses in narratives
New Auto-Interp
Negative Logits
':[
-0.16
[[
-0.16
'{}'-0.15
("(%-0.15
([]*
-0.15
(',');↵-0.15
'[
-0.15
'])[
-0.15
#${-0.15
=[[
-0.14
POSITIVE LOGITS
("0.58
(“
0.56
("0.53
["
0.48
{"0.45
["
0.42
{"0.41
_("0.40
=("0.38
)("0.36
Activations Density 0.096%