INDEX
Explanations
technical terms related to software analysis and programming
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1482
+0.13
0.4%
200
+0.13
0.4%
680
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
200
+0.13
0.02
1443
+0.13
0.02
1482
+0.11
0.02
Negative Logits
shenan
-1.40
impra
-1.39
maneu
-1.33
reluct
-1.32
encomp
-1.32
unve
-1.32
depic
-1.29
increa
-1.29
disagre
-1.26
reconno
-1.25
POSITIVE LOGITS
static
1.18
static
1.15
Static
1.09
STATIC
1.04
Static
0.99
isStatic
0.89
静态
0.79
静
0.74
statics
0.71
fixed
0.71
Activations Density 0.135%