INDEX
Explanations
locations and events related to political protests
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1013
+0.15
0.5%
964
+0.14
0.4%
906
+0.14
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
964
+0.15
0.06
1013
+0.14
0.07
939
+0.14
0.06
Negative Logits
tupperware
-0.99
hairc
-0.99
peppa
-0.95
cushi
-0.94
🤣🤣
-0.87
Lmao
-0.87
lmfao
-0.86
broderie
-0.85
riviera
-0.85
:'(
-0.85
POSITIVE LOGITS
downtown
0.56
Palace
0.55
Plaza
0.54
City
0.51
Square
0.49
losseum
0.49
streets
0.48
iconic
0.47
City
0.47
Downtown
0.47
Activations Density 0.473%