INDEX
Explanations
references to mass events or large-scale phenomena
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1023
+0.13
0.5%
871
+0.13
0.5%
1870
+0.13
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1023
+0.13
0.03
1573
+0.13
0.03
1331
+0.13
0.03
Negative Logits
แท
-0.51
-0.49
EditorBrowsable
-0.49
<bos>
-0.49
NewReader
-0.48
.
-0.48
On
-0.48
;->
-0.48
FormBorderStyle
-0.47
Go
-0.47
POSITIVE LOGITS
suspic
1.55
emphat
1.49
tranf
1.48
ftu
1.48
ftre
1.46
milf
1.45
perfon
1.45
swarovski
1.44
excru
1.42
greate
1.42
Activations Density 0.086%