INDEX
Explanations
proper nouns of locations and names related to outdoor activities and technology
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
528
+0.18
1.1%
1145
+0.14
0.9%
1052
+0.13
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
690
+0.18
0.07
528
+0.14
0.06
1013
+0.13
0.12
Negative Logits
<bos>
-2.74
retrouve
-0.79
jette
-0.76
sienta
-0.75
вашем
-0.73
san
-0.72
public
-0.71
ApiModelProperty
-0.71
remet
-0.71
sen
-0.71
POSITIVE LOGITS
reluct
2.23
disagre
2.20
disreg
2.16
affor
2.16
increa
2.15
jorge
2.14
suscep
2.11
accla
2.10
impra
2.09
maneu
2.09
Activations Density 1.898%