INDEX
Explanations
contact information in an email format
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1343
+0.17
0.5%
736
+0.11
0.3%
227
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
981
+0.17
0.02
294
+0.11
0.01
782
+0.10
0.02
Negative Logits
Pyrene
-0.79
chery
-0.79
claudia
-0.73
tolerably
-0.71
fua
-0.70
budapest
-0.69
wien
-0.69
pyridine
-0.68
vainly
-0.68
mallorca
-0.67
POSITIVE LOGITS
>@
0.66
asteroide
0.63
conva
0.62
.@
0.62
conclud
0.61
-@
0.61
solidar
0.61
riten
0.60
Interess
0.60
$@
0.59
Activations Density 0.033%