INDEX
Explanations
currency-related terms and values
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
342
+0.14
0.8%
277
+0.13
0.7%
186
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
342
+0.14
0.05
20
+0.13
0.13
78
+0.12
0.03
Negative Logits
oxford
-1.63
ey
-1.58
uel
-1.52
unds
-1.49
ively
-1.39
states
-1.36
rounds
-1.32
uest
-1.31
+)
-1.29
consec
-1.29
POSITIVE LOGITS
\":
1.93
¿½
1.80
"}](#
1.67
ILITY
1.64
---|---
1.58
à«ĩ
1.51
Į
1.51
kerchief
1.46
ieur
1.46
\]](
1.46
Activations Density 4.644%