INDEX
Explanations
references to copper and its various uses or contexts in the document
New Auto-Interp
Negative Logits
asy
-0.20
umes
-0.17
egin
-0.15
asley
-0.14
aler
-0.14
Humb
-0.14
bben
-0.14
ift
-0.14
isman
-0.14
cki
-0.14
POSITIVE LOGITS
mith
0.17
foil
0.17
belt
0.17
illez
0.16
nick
0.16
leaf
0.16
wire
0.15
ISON
0.15
finger
0.15
plate
0.15
Activations Density 0.007%