INDEX
Explanations
mentions of holidays and celebrations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1438
+0.13
0.4%
1741
+0.12
0.4%
1870
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1438
+0.13
0.07
1984
+0.12
0.07
1870
+0.10
0.04
Negative Logits
GEBURTSDATUM
-0.88
autorytatywna
-0.79
WriteBarrier
-0.76
下载附件
-0.72
kasarigan
-0.70
DeleteBehavior
-0.70
fjspx
-0.69
Datuak
-0.69
الإنجليزية
-0.69
وتسجيلات
-0.68
POSITIVE LOGITS
drap
0.87
ankara
0.86
Mâ
0.86
Godt
0.84
↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
0.83
banane
0.82
Malte
0.81
:)</
0.81
hcm
0.80
↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
0.79
Activations Density 0.768%