INDEX
Explanations
phrases related to medical surgeries and health issues
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1870
+0.12
0.4%
1325
+0.12
0.4%
1406
+0.10
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1256
+0.12
0.02
505
+0.12
0.01
1565
+0.10
0.02
Negative Logits
volunte
-0.68
scrat
-0.67
laun
-0.65
intermitt
-0.64
effe
-0.62
auricular
-0.62
accla
-0.61
erad
-0.61
osse
-0.58
intere
-0.58
POSITIVE LOGITS
surgery
1.29
Surgery
1.17
surgeries
1.03
surgery
1.01
surgical
0.99
surgeon
0.94
surgeons
0.93
Surgery
0.93
urgery
0.90
surgical
0.85
Activations Density 0.078%