INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.31
1.3%
1870
+0.06
0.2%
1253
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.31
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
unspeak
-2.22
belliger
-1.98
ineffec
-1.94
ruinous
-1.93
miscon
-1.90
horrend
-1.88
laug
-1.83
vainly
-1.81
odious
-1.81
unavoid
-1.79
POSITIVE LOGITS
<bos>
11.17
GEBURTSDATUM
2.62
expandindo
2.55
Autoritní
2.19
betweenstory
2.14
kasarigan
2.12
تقاوى
2.01
Italijani
2.00
Италијани
2.00
Paglinawan
1.97
Activations Density 0.000%
No Known Activations
This feature has no known activations.