INDEX
Explanations
words related to bricks and structures made of bricks
mentions of bricks and brick-related themes
New Auto-Interp
Negative Logits
ntil
-0.78
ktop
-0.75
Voters
-0.73
judicial
-0.72
selection
-0.71
etheus
-0.69
inen
-0.67
uthor
-0.67
ffect
-0.65
pmwiki
-0.64
POSITIVE LOGITS
bats
1.27
layer
1.13
mort
0.97
yard
0.96
shaw
0.95
bricks
0.95
brick
0.90
works
0.90
buster
0.89
Brick
0.84
Activations Density 0.010%