INDEX
Explanations
references to prior events or instances
New Auto-Interp
Negative Logits
former
-0.17
former
-0.16
currently
-0.15
uck
-0.15
currently
-0.15
缮åīį
-0.15
inals
-0.14
etic
-0.14
anc
-0.14
thing
-0.14
POSITIVE LOGITS
/current
0.34
-generation
0.28
carousel
0.25
/original
0.22
zeitig
0.20
ebin
0.20
mente
0.20
generations
0.19
lys
0.18
incarnation
0.18
Activations Density 0.036%