INDEX
Explanations
names and titles related to events or ceremonies, such as officiants, venues, and schedules
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1044
+0.10
0.3%
2000
+0.10
0.3%
1328
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1044
+0.10
0.03
1363
+0.10
0.03
1343
+0.10
0.03
Negative Logits
<bos>
-0.79
vo
-0.61
باز
-0.60
Бі
-0.57
Alemania
-0.57
shouldn
-0.56
should
-0.55
ale
-0.55
export
-0.54
社
-0.54
POSITIVE LOGITS
ord
2.39
ORD
1.91
ords
1.84
ordina
1.83
ord
1.75
ORD
1.75
Ord
1.73
Ord
1.66
CORD
1.65
Cord
1.57
Activations Density 0.205%