INDEX
Explanations
information related to gameplay features, such as items, play modes, and interactions with other players
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
678
+0.13
0.4%
50
+0.11
0.3%
1403
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1551
+0.13
0.04
678
+0.11
0.05
1415
+0.10
0.02
Negative Logits
especie
-0.66
NewUrlParser
-0.58
toluene
-0.58
Tetrach
-0.57
thylene
-0.57
<bos>
-0.56
propan
-0.56
]<=
-0.55
zzlement
-0.55
Bioaccumulative
-0.54
POSITIVE LOGITS
apprehen
1.75
impra
1.69
reluct
1.67
intersper
1.65
disagre
1.63
resear
1.63
indestru
1.62
encomp
1.62
accla
1.55
coö
1.55
Activations Density 0.694%