INDEX
Explanations
phrases related to political events and actions related to a government
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
51
+0.17
0.5%
304
+0.14
0.5%
1380
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
51
+0.17
0.04
749
+0.14
0.03
16
+0.12
0.04
Negative Logits
Casi
-1.03
Bajo
-0.90
Cuatro
-0.88
tarjetas
-0.86
Desta
-0.86
Recomend
-0.86
livro
-0.86
Embal
-0.85
Precis
-0.85
painel
-0.84
POSITIVE LOGITS
„,
2.73
mef
2.72
wien
2.69
dises
2.67
seiz
2.58
nutr
2.53
exem
2.50
stockholm
2.49
effe
2.48
blos
2.46
Activations Density 0.173%