INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.37
2.0%
344
+0.04
0.2%
823
+0.04
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.37
0.00
0
-0.04
0.00
1
-0.04
0.00
Negative Logits
unspeak
-1.64
belliger
-1.48
ruinous
-1.35
miscon
-1.33
exasper
-1.33
ineffectual
-1.31
demoral
-1.31
despotism
-1.30
unbear
-1.29
odious
-1.27
POSITIVE LOGITS
<bos>
12.34
Autoritní
2.30
GEBURTSDATUM
2.30
betweenstory
2.19
expandindo
2.19
Paglinawan
2.05
'\\;'
1.99
تقاوى
1.96
Administrativna
1.95
autorytatywna
1.95
Activations Density 0.000%
No Known Activations
This feature has no known activations.