INDEX
Explanations
expressions of disappointment and critique related to narratives
New Auto-Interp
Negative Logits
Maver
-0.16
wstring
-0.15
theid
-0.14
rai
-0.14
naken
-0.14
ICI
-0.14
VIR
-0.14
icÃŃ
-0.14
¯¼
-0.14
vir
-0.14
POSITIVE LOGITS
Count
0.28
Counts
0.25
Handler
0.25
Sn
0.24
counts
0.22
Count
0.21
-count
0.21
count
0.21
Ol
0.21
Sn
0.21
Activations Density 0.003%