INDEX
Explanations
mentions of a specific drug called Apitvus
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
313
+0.11
0.4%
1896
+0.08
0.3%
553
+0.07
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1059
+0.11
0.03
1637
+0.08
0.03
1343
+0.07
0.03
Negative Logits
<bos>
-0.94
、
-0.80
.
-0.80
,
-0.79
-0.79
-0.78
…
-0.78
-0.78
managed
-0.77
itemize
-0.77
POSITIVE LOGITS
Khart
2.41
stockholm
2.33
maneu
2.29
mef
2.26
wien
2.25
Hez
2.23
effe
2.23
fep
2.20
Juf
2.20
emphat
2.20
Activations Density 0.091%