INDEX
Explanations
references to American football, particularly quarterbacks, and discussions about different viewpoints or opinions on the subject
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1705
+0.09
0.3%
2006
+0.09
0.3%
2034
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2006
+0.09
0.06
729
+0.09
0.05
342
+0.08
0.05
Negative Logits
strick
-1.11
increa
-1.09
volunte
-1.07
squa
-1.06
milf
-1.05
?...
-1.04
accla
-1.03
fuf
-1.02
maneu
-1.02
guarante
-1.01
POSITIVE LOGITS
available
0.79
waiting
0.75
worauf
0.72
ready
0.70
womit
0.67
whose
0.65
capable
0.64
coming
0.62
that
0.62
zumal
0.62
Activations Density 0.402%