INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.38
2.5%
1870
+0.07
0.4%
1741
+0.06
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.38
0.00
0
-0.07
0.00
1
-0.06
0.00
Negative Logits
unspeak
-2.29
ineffec
-2.13
horrend
-2.12
belliger
-2.07
ruinous
-1.99
laug
-1.97
miscon
-1.97
disgra
-1.95
unavoid
-1.95
unlaw
-1.93
POSITIVE LOGITS
<bos>
13.14
GEBURTSDATUM
2.78
expandindo
2.71
betweenstory
2.54
Autoritní
2.51
kasarigan
2.32
'\\;'
2.24
Administrativna
2.23
Italijani
2.19
Paglinawan
2.16
Activations Density 0.000%
No Known Activations
This feature has no known activations.