INDEX
Explanations
phrases, words, and concepts related to cooking mistakes
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.17
0.9%
161
+0.10
0.5%
1548
+0.10
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1601
+0.17
0.03
1363
+0.10
0.03
36
+0.10
0.03
Negative Logits
<bos>
-3.61
public
-0.75
-0.72
enumerate
-0.71
foreach
-0.70
struct
-0.70
provide
-0.70
look
-0.70
<eos>
-0.70
echo
-0.69
POSITIVE LOGITS
stockholm
2.17
Minang
2.11
bandung
2.00
Juf
1.98
aen
1.94
lele
1.93
fta
1.93
wien
1.92
mef
1.92
meis
1.91
Activations Density 0.109%