INDEX
Explanations
mentions of specific types of home building materials, specifically tiles
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
82
+0.16
0.8%
1262
+0.14
0.7%
1961
+0.14
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1385
+0.16
0.05
1013
+0.14
0.04
690
+0.14
0.03
Negative Logits
<bos>
-1.27
كومونز
-0.75
Perci
-0.74
encomp
-0.74
Molto
-0.73
Più
-0.73
springfox
-0.72
Stretcher
-0.71
Abbiamo
-0.70
Altri
-0.70
POSITIVE LOGITS
tile
1.48
tiles
1.40
Tile
1.29
Tile
1.27
tile
1.24
Tiles
1.22
tiles
1.14
Tiles
1.07
TILE
1.06
tiled
1.03
Activations Density 0.395%