INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.26
1.0%
1870
+0.07
0.3%
1725
+0.06
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.26
0.00
0
-0.07
0.00
1
-0.06
0.00
Negative Logits
so
-0.80
undermines
-0.79
also
-0.77
humiliating
-0.77
apparently
-0.76
couldn
-0.75
thwarted
-0.74
were
-0.73
dumbfounded
-0.73
they
-0.73
POSITIVE LOGITS
<bos>
9.69
dispen
1.90
GEBURTSDATUM
1.85
fta
1.77
effe
1.75
desir
1.74
squa
1.74
ftu
1.70
nutr
1.69
fto
1.69
Activations Density 0.000%
No Known Activations
This feature has no known activations.