INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.31
1.4%
1870
+0.05
0.2%
1120
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.31
0.00
0
-0.05
0.00
1
-0.05
0.00
Negative Logits
unspeak
-2.72
ineffec
-2.33
horrend
-2.29
shenan
-2.26
disgra
-2.20
belliger
-2.19
apprehen
-2.18
ruinous
-2.18
reluct
-2.16
exasper
-2.16
POSITIVE LOGITS
<bos>
11.89
GEBURTSDATUM
2.69
expandindo
2.65
Autoritní
2.32
betweenstory
2.27
kasarigan
2.16
Paglinawan
2.14
تقاوى
2.11
Italijani
2.09
Италијани
2.09
Activations Density 0.000%
No Known Activations
This feature has no known activations.