INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.33
1.3%
1120
+0.06
0.2%
381
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.33
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
unspeak
-2.15
belliger
-1.92
disgra
-1.88
ruinous
-1.84
ineffec
-1.82
exasper
-1.79
horrend
-1.78
impractica
-1.77
shenan
-1.76
indestru
-1.74
POSITIVE LOGITS
<bos>
11.04
expandindo
2.29
GEBURTSDATUM
2.11
betweenstory
2.02
'\\;'
1.95
Administrativna
1.89
Autoritní
1.83
تقاوى
1.83
LookAnd
1.77
Italijani
1.75
Activations Density 0.000%
No Known Activations
This feature has no known activations.