INDEX
Explanations
mentions of the word "diamond" in various contexts
New Auto-Interp
Negative Logits
figcaption
-0.15
apon
-0.15
emin
-0.14
venir
-0.14
ng
-0.14
дом
-0.14
stral
-0.14
entar
-0.14
ivan
-0.14
onder
-0.14
POSITIVE LOGITS
backs
0.22
-shaped
0.20
ifer
0.19
jub
0.18
Jub
0.18
back
0.17
opoulos
0.17
ring
0.17
shaped
0.17
dust
0.17
Activations Density 0.016%