INDEX
Explanations
references to the present time or present-day events
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
554
+0.12
0.4%
479
+0.11
0.4%
1339
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
554
+0.12
0.03
1480
+0.11
0.03
479
+0.11
0.02
Negative Logits
jä
-0.51
cajones
-0.50
lü
-0.49
FontWeight
-0.47
<<"
-0.46
kateg
-0.46
}}">
-0.45
leyenda
-0.44
}}"
-0.44
<<"
-0.44
POSITIVE LOGITS
Present
1.20
PRESENT
1.14
Present
1.14
present
1.11
present
1.07
hairc
0.99
perfet
0.97
milf
0.93
shenan
0.91
simpsons
0.90
Activations Density 0.063%