INDEX
Explanations
references to political votes and legislation
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1499
+0.09
0.3%
776
+0.08
0.2%
1150
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
16
+0.09
0.06
1499
+0.08
0.05
1683
+0.08
0.05
Negative Logits
pinulongan
-0.49
yogur
-0.47
chauung
-0.47
usstsein
-0.46
getPost
-0.46
незавершена
-0.46
odkazy
-0.45
ContentAsync
-0.44
FetchType
-0.43
deleteUser
-0.43
POSITIVE LOGITS
proposals
0.73
seoul
0.69
proposal
0.67
proposed
0.67
Proposed
0.65
secon
0.64
shenan
0.63
giù
0.63
Proposals
0.63
hcm
0.62
Activations Density 0.427%