INDEX
Explanations
mentions of specific product names and financial information
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
690
+0.14
0.4%
1150
+0.13
0.4%
478
+0.13
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
227
+0.14
0.06
690
+0.13
0.03
324
+0.13
0.03
Negative Logits
Ottobre
-1.09
affez
-1.04
saurait
-0.92
Chá
-0.92
Settembre
-0.91
Novembre
-0.91
ivi
-0.91
solidar
-0.91
sappi
-0.90
lomb
-0.89
POSITIVE LOGITS
unspeak
1.06
vainly
1.05
apprehen
1.02
shenan
0.99
gaily
0.98
indescri
0.97
tolerably
0.90
mischie
0.86
impelled
0.86
ineffec
0.85
Activations Density 0.278%