INDEX
Explanations
keywords related to software licensing
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
23
+0.19
1.2%
53
+0.15
1.0%
478
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
53
+0.19
0.06
273
+0.15
0.03
333
+0.12
0.03
Negative Logits
zent
-1.69
/#
-1.61
ém
-1.51
ography
-1.49
combo
-1.49
mog
-1.49
ics
-1.39
Warriors
-1.36
ict
-1.34
eric
-1.34
POSITIVE LOGITS
ŀ
1.90
Ĥ
1.87
»
1.78
ģ
1.72
ashamed
1.57
ĨĴ
1.56
ķ
1.54
Īĺ
1.53
LLOW
1.53
¿½
1.44
Activations Density 0.330%