INDEX
Explanations
terms related to computer programming, tools, coding languages, and technology infrastructure
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1994
+0.15
0.8%
1068
+0.12
0.6%
1624
+0.11
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1994
+0.15
0.03
1870
+0.12
0.01
783
+0.11
0.02
Negative Logits
<bos>
-1.37
-0.89
shenan
-0.88
ⓧ
-0.84
vainly
-0.81
disambigu
-0.80
sophistic
-0.78
McLaugh
-0.76
poetical
-0.76
<?
-0.74
POSITIVE LOGITS
programming
1.38
Programming
1.31
Programming
1.29
programming
1.25
programmer
1.06
programmer
0.97
programmers
0.92
Programmer
0.89
thuy
0.88
programación
0.87
Activations Density 0.357%