INDEX
Explanations
dates in a specific format
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
200
+0.14
0.4%
897
+0.13
0.4%
1837
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
200
+0.14
0.06
1837
+0.13
0.06
397
+0.11
0.05
Negative Logits
EEU
-0.75
createdBy
-0.74
michelin
-0.68
increa
-0.68
userEmail
-0.66
bayern
-0.64
dci
-0.63
userType
-0.63
stockholm
-0.63
responseData
-0.62
POSITIVE LOGITS
last
0.90
Last
0.85
Last
0.81
last
0.81
LAST
0.79
<bos>
0.76
setLast
0.73
LAST
0.73
getLast
0.67
week
0.61
Activations Density 0.075%