INDEX
Explanations
quantitative data and specific parameters in scientific contexts
New Auto-Interp
Negative Logits
út
-0.18
apol
-0.16
æĺ
-0.16
utar
-0.16
客
-0.15
fen
-0.14
ADER
-0.14
инг
-0.13
anny
-0.13
PW
-0.13
POSITIVE LOGITS
cavity
0.27
cav
0.25
mode
0.23
opt
0.23
squeezing
0.22
modes
0.21
Cav
0.21
Modes
0.21
squeezed
0.20
squeez
0.20
Activations Density 0.004%