INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.23
0.7%
1363
+0.06
0.2%
164
+0.06
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.23
0.00
0
-0.06
0.00
1
-0.06
0.00
Negative Logits
unspeak
-1.21
unlaw
-1.20
impractica
-1.17
disgra
-1.13
despotism
-1.11
belliger
-1.07
unwarran
-1.03
miscon
-1.02
ruinous
-1.01
calum
-0.99
POSITIVE LOGITS
<bos>
8.06
expandindo
1.60
GEBURTSDATUM
1.39
Autoritní
1.34
betweenstory
1.30
تقاوى
1.28
Италијани
1.28
'\\;'
1.24
脚注の使い方
1.24
LookAnd
1.22
Activations Density 0.000%
No Known Activations
This feature has no known activations.