INDEX
Explanations
references to legal or bureaucratic documents
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1741
+0.30
1.1%
50
+0.17
0.6%
1535
+0.13
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1045
+0.30
0.05
397
+0.17
0.04
241
+0.13
0.05
Negative Logits
shenan
-0.81
withal
-0.74
disreg
-0.73
maneu
-0.71
friable
-0.71
intersper
-0.70
subgoals
-0.69
apprehen
-0.68
diffusi
-0.67
gaily
-0.67
POSITIVE LOGITS
Katso
0.79
prouve
0.78
Glej
0.74
préc
0.74
Mitä
0.73
légiti
0.67
gouver
0.67
Thé
0.66
prétend
0.65
Guzmán
0.62
Activations Density 0.216%