INDEX
Explanations
numerical patterns and calculations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1978
+0.22
0.8%
382
+0.15
0.6%
1515
+0.13
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
382
+0.22
0.07
1515
+0.15
0.05
1187
+0.13
0.04
Negative Logits
Autoritní
-0.75
smtplib
-0.73
glaubte
-0.67
Pekan
-0.67
ffilm
-0.66
Embaj
-0.60
Mə
-0.60
もしろ
-0.59
Manbalar
-0.58
הע
-0.57
POSITIVE LOGITS
1
0.97
0
0.75
2
0.70
¹
0.67
3
0.62
5
0.61
Methanol
0.60
4
0.60
6
0.59
9
0.59
Activations Density 0.229%