INDEX
Explanations
phrases related to large institutions or entities
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
781
+0.11
0.3%
198
+0.11
0.3%
270
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
270
+0.11
0.05
781
+0.11
0.04
1561
+0.09
0.04
Negative Logits
définitivement
-0.53
autrement
-0.52
WebServlet
-0.51
Тарихы
-0.51
spania
-0.50
initComponents
-0.49
exorbit
-0.49
withal
-0.48
Felsen
-0.48
plenti
-0.48
POSITIVE LOGITS
largest
0.64
largest
0.62
santiago
0.56
tucson
0.55
Juárez
0.55
Asunción
0.55
hcm
0.52
Vitória
0.52
nevada
0.51
churrasco
0.50
Activations Density 0.239%