INDEX
Explanations
mentions of measurements related to length
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1385
+0.12
0.4%
86
+0.10
0.3%
36
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
86
+0.12
0.03
1110
+0.10
0.03
1705
+0.10
0.03
Negative Logits
squa
-1.37
fortn
-1.37
secon
-1.34
volunte
-1.31
encomp
-1.31
affor
-1.27
reluct
-1.26
oner
-1.26
increa
-1.24
tew
-1.23
POSITIVE LOGITS
inches
0.99
inch
0.95
inch
0.81
inches
0.79
diameter
0.75
width
0.69
height
0.66
thickness
0.63
size
0.60
feet
0.60
Activations Density 0.085%