INDEX
Explanations
references to articles from "The New York Times"
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1741
+0.15
0.4%
1013
+0.09
0.3%
781
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1997
+0.15
0.04
1992
+0.09
0.03
613
+0.09
0.03
Negative Logits
ftu
-1.57
§.
-1.51
broderie
-1.50
fta
-1.49
»>
-1.46
aen
-1.45
aquarelle
-1.45
wien
-1.44
matel
-1.44
tranf
-1.43
POSITIVE LOGITS
Times
0.93
Times
0.87
newspaper
0.78
’
0.68
times
0.67
nytimes
0.66
paper
0.66
News
0.64
'
0.63
TIMES
0.62
Activations Density 0.090%