INDEX
Explanations
dates and numbers related to political events or elections
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1978
+0.12
0.3%
776
+0.09
0.3%
208
+0.09
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
573
+0.12
0.04
499
+0.09
0.04
776
+0.09
0.04
Negative Logits
liberality
-1.24
unwarran
-1.18
felicity
-1.14
impractica
-1.12
shewn
-1.09
beaute
-1.05
unspeak
-1.02
loveliness
-1.01
indestru
-1.00
hairc
-0.99
POSITIVE LOGITS
kosme
1.47
kompati
1.40
alkoh
1.39
elek
1.38
praktik
1.37
akut
1.32
antik
1.32
kollek
1.32
silikon
1.31
mikrofon
1.31
Activations Density 0.132%