INDEX
Explanations
topics related to political events, government actions, and public demonstrations within specific countries
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
752
+0.14
0.4%
1967
+0.10
0.3%
421
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
704
+0.14
0.02
752
+0.10
0.03
16
+0.10
0.03
Negative Logits
WireFormat
-0.62
Jereo
-0.60
nahilalakip
-0.59
UrlResolution
-0.59
ביוגרפיה
-0.58
Sqft
-0.57
]")]
-0.57
ConstraintMaker
-0.55
DoubleQuotes
-0.54
!("{}",-0.54
POSITIVE LOGITS
Gorb
1.14
Knud
1.14
Bartholo
1.09
reluct
1.09
philanth
1.08
pamph
1.05
McLaugh
1.04
Schrö
1.03
Mlle
1.01
Intere
1.00
Activations Density 0.119%