INDEX
Explanations
copyright-related phrases
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.25
1.0%
204
+0.10
0.4%
1264
+0.10
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1124
+0.25
0.05
1264
+0.10
0.05
537
+0.10
0.04
Negative Logits
<bos>
-2.76
AssemblyCompany
-0.73
amoan
-0.69
InputBorder
-0.67
EndProject
-0.67
glBind
-0.65
beforeEach
-0.61
BindingResult
-0.61
toContain
-0.61
sendRedirect
-0.59
POSITIVE LOGITS
maneu
1.39
milf
1.39
affor
1.36
accla
1.33
practition
1.33
pollut
1.31
stockholm
1.25
volunte
1.21
opport
1.21
attemp
1.20
Activations Density 0.226%