INDEX
Explanations
references to children's literature and related authors
New Auto-Interp
Negative Logits
aise
-0.17
infeld
-0.15
lect
-0.15
zion
-0.15
edish
-0.15
u
-0.15
ÑģÑħод
-0.15
Essays
-0.14
ae
-0.14
Rew
-0.13
POSITIVE LOGITS
picture
0.35
picture
0.30
Picture
0.29
Picture
0.25
-picture
0.24
_picture
0.24
illustrator
0.22
.picture
0.22
pictures
0.20
children
0.19
Activations Density 0.175%