INDEX
Explanations
locations or objects related to dens
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1491
+0.17
0.7%
1323
+0.17
0.7%
228
+0.14
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1491
+0.17
0.03
1323
+0.17
0.02
228
+0.14
0.02
Negative Logits
raud
-0.48
jenem
-0.45
familiari
-0.42
chwitz
-0.42
Vicksburg
-0.40
Baird
-0.39
Saratoga
-0.39
bootstra
-0.38
coordinate
-0.38
COORD
-0.38
POSITIVE LOGITS
DEN
1.24
Den
1.21
Den
1.12
den
1.10
DEN
1.02
den
0.92
Dens
0.92
susun
0.86
tanong
0.84
dens
0.82
Activations Density 0.081%