INDEX
Explanations
locations in Manhattan
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
805
+0.12
0.4%
897
+0.10
0.3%
1052
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
648
+0.12
0.04
227
+0.10
0.05
438
+0.10
0.05
Negative Logits
Ottobre
-0.81
šech
-0.70
sappi
-0.67
affez
-0.66
exé
-0.65
brille
-0.64
Luglio
-0.63
soggior
-0.62
Giugno
-0.62
letti
-0.62
POSITIVE LOGITS
NYC
1.19
Manhattan
1.04
NYC
1.01
NY
1.00
NYPD
0.97
Brooklyn
0.94
NY
0.93
nyc
0.91
Bronx
0.91
nyc
0.90
Activations Density 0.262%