INDEX
Explanations
references to specific historical events and individuals
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.25
1.0%
198
+0.09
0.4%
1013
+0.07
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
776
+0.25
0.09
1409
+0.09
0.05
17
+0.07
0.08
Negative Logits
<bos>
-2.78
continue
-0.69
<eos>
-0.67
@
-0.66
HasIndex
-0.65
confirm
-0.65
add
-0.63
assist
-0.62
addComponent
-0.62
sit
-0.62
POSITIVE LOGITS
Juf
1.70
bandung
1.67
maneu
1.63
emphat
1.61
jaya
1.59
maroc
1.58
affor
1.55
Minang
1.55
disagre
1.53
lele
1.53
Activations Density 1.543%