INDEX
Explanations
occurrences of the word "proposal"
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1870
+0.13
0.5%
11
+0.12
0.4%
553
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
11
+0.13
0.02
553
+0.12
0.02
874
+0.12
0.02
Negative Logits
pessi
-0.62
patrio
-0.60
broderie
-0.58
ceptre
-0.58
statis
-0.57
discogs
-0.57
exciter
-0.57
monot
-0.55
solidar
-0.55
BIBSYS
-0.54
POSITIVE LOGITS
proposal
1.31
proposals
1.29
proposal
1.17
Proposal
1.11
Proposal
1.08
Proposals
1.07
Proposals
1.00
proposes
0.97
proposals
0.96
proposing
0.96
Activations Density 0.031%