INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.34
1.2%
381
+0.06
0.2%
144
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.34
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
unspeak
-1.12
ruinous
-1.09
horrend
-1.08
belliger
-1.07
unbear
-1.05
laug
-1.04
unfore
-1.04
unavoid
-1.03
ineffectual
-1.01
nukes
-1.00
POSITIVE LOGITS
<bos>
9.78
expandindo
2.00
GEBURTSDATUM
2.00
betweenstory
1.68
Италијани
1.66
Autoritní
1.65
parteci
1.65
'\\;'
1.62
Administrativna
1.58
Geplaatst
1.57
Activations Density 0.000%
No Known Activations
This feature has no known activations.