INDEX
Explanations
mentions of bookmarks or links to posts
New Auto-Interp
Negative Logits
phans
-0.17
jamin
-0.15
abouts
-0.14
alez
-0.14
Lyons
-0.14
ower
-0.14
_blob
-0.14
aka
-0.14
acky
-0.14
tow
-0.14
POSITIVE LOGITS
/Foundation
0.17
Track
0.16
track
0.15
егÑĢа
0.15
Track
0.15
follow
0.15
atoms
0.15
Comments
0.15
uis
0.14
comments
0.14
Activations Density 0.006%