INDEX
Explanations
mentions of specific names or individuals such as "Arpaio," "Mohler-Faria," "Nely," "Thorkildsen," and "Concannon."
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1177
+0.14
0.5%
1978
+0.14
0.4%
453
+0.13
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
981
+0.14
0.07
1001
+0.14
0.05
1177
+0.13
0.03
Negative Logits
<bos>
-1.54
/*---
-0.61
وض
-0.58
لينكات
-0.57
서울
-0.56
소녀
-0.56
no
-0.56
나는
-0.56
mamy
-0.55
头像
-0.54
POSITIVE LOGITS
Bartholo
1.60
deleter
1.59
alre
1.59
effe
1.58
fta
1.58
Gorb
1.56
Juf
1.56
secon
1.55
mef
1.52
overla
1.52
Activations Density 0.231%