INDEX
Explanations
mentions of journalism, media, and news production
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1842
+0.27
0.8%
394
+0.17
0.5%
1577
+0.12
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1796
+0.27
0.04
1694
+0.17
0.05
683
+0.12
0.07
Negative Logits
unwarran
-1.06
disagre
-1.00
encomp
-1.00
nutella
-0.99
McLaugh
-0.98
swarovski
-0.98
considér
-0.96
impra
-0.95
prêtres
-0.92
scrat
-0.92
POSITIVE LOGITS
topics
0.68
news
0.66
arit
0.64
tages
0.63
tami
0.59
reporta
0.59
information
0.59
dita
0.58
events
0.57
content
0.57
Activations Density 0.818%