INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.30
1.0%
166
+0.06
0.2%
1593
+0.05
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.30
0.00
0
-0.06
0.00
1
-0.05
0.00
Negative Logits
unspeak
-3.07
reluct
-2.93
shenan
-2.83
impra
-2.75
disagre
-2.69
ineffec
-2.63
apprehen
-2.57
increa
-2.56
depic
-2.53
indescri
-2.49
POSITIVE LOGITS
<bos>
9.30
GEBURTSDATUM
2.04
Autoritní
2.02
'\\;'
1.95
expandindo
1.92
betweenstory
1.91
Paglinawan
1.88
Walkover
1.87
LookAnd
1.84
Himo
1.77
Activations Density 0.000%
No Known Activations
This feature has no known activations.