INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.23
0.7%
630
+0.06
0.2%
958
+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
-1.58
impelled
-1.34
unavoid
-1.31
horrend
-1.28
ineffec
-1.26
Considerable
-1.26
McLaugh
-1.26
belliger
-1.26
laug
-1.25
wilfully
-1.23
POSITIVE LOGITS
<bos>
7.08
sappi
1.93
Ottobre
1.87
abbra
1.86
affez
1.85
GEBURTSDATUM
1.81
parteci
1.80
expandindo
1.78
torner
1.75
betweenstory
1.73
Activations Density 0.000%
No Known Activations
This feature has no known activations.