INDEX
Explanations
points of emphasis or importance in a text
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
481
+0.14
0.5%
1677
+0.12
0.5%
699
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
699
+0.14
0.03
481
+0.12
0.02
1677
+0.12
0.02
Negative Logits
Décembre
-0.86
compréhen
-0.81
Perci
-0.77
sappi
-0.77
Février
-0.76
Messieurs
-0.74
Áng
-0.74
gettyimages
-0.73
Secrétaire
-0.70
depositphotos
-0.68
POSITIVE LOGITS
highlights
1.13
highlight
1.13
highlighting
1.02
highlighted
0.96
highlight
0.94
Highlight
0.89
Highlight
0.89
Highlights
0.89
highlights
0.88
Highlights
0.83
Activations Density 0.078%