INDEX
Explanations
descriptions related to physical pain and injuries
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1387
+0.17
0.6%
1472
+0.13
0.5%
1909
+0.12
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1387
+0.17
0.04
1909
+0.13
0.03
1472
+0.12
0.02
Negative Logits
āci
-0.51
meras
-0.51
GoogleFonts
-0.48
tâ
-0.47
Lähteet
-0.47
puto
-0.46
baku
-0.46
Portale
-0.46
vinaigre
-0.46
levure
-0.45
POSITIVE LOGITS
pain
1.32
Pain
1.30
Pain
1.28
PAIN
1.23
pain
1.21
pains
0.95
paink
0.80
painel
0.79
pained
0.78
painful
0.74
Activations Density 0.061%