INDEX
Explanations
locations such as streets and avenues
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1013
+0.18
0.5%
964
+0.14
0.4%
1741
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
964
+0.18
0.04
1013
+0.14
0.03
723
+0.10
0.03
Negative Logits
imparare
-0.93
succede
-0.86
dicono
-0.84
aspetta
-0.81
rispond
-0.81
scopri
-0.79
affez
-0.79
abbiano
-0.78
scoprire
-0.77
Ottobre
-0.76
POSITIVE LOGITS
impelled
0.87
McLaugh
0.85
McInt
0.85
unspeak
0.82
shenan
0.81
gaily
0.79
vainly
0.79
roused
0.78
Gorb
0.78
apprehen
0.78
Activations Density 0.087%