INDEX
Explanations
phrases related to chronological events or sequences
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1964
+0.16
0.6%
597
+0.16
0.6%
1096
+0.15
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1964
+0.16
0.05
1096
+0.16
0.04
597
+0.15
0.04
Negative Logits
MET
-0.50
Även
-0.48
Ro
-0.47
Cho
-0.47
Bra
-0.47
Bra
-0.47
Ra
-0.46
Asimismo
-0.46
UObject
-0.46
letter
-0.45
POSITIVE LOGITS
SINCE
1.01
bordeaux
0.90
affez
0.85
unce
0.85
poichè
0.85
ecru
0.83
ciga
0.83
cannes
0.82
encomp
0.82
shenan
0.81
Activations Density 0.074%