INDEX
Explanations
programming syntax elements and expressions
New Auto-Interp
Negative Logits
kerk
-0.46
particle
-0.41
church
-0.40
œil
-0.39
stone
-0.38
dumne
-0.38
meisje
-0.38
paard
-0.36
pouvoit
-0.35
piedra
-0.35
POSITIVE LOGITS
kaarangay
0.75
avatar
0.73
rungsseite
0.73
🔕
0.73
phenotype
0.71
<unused52>
0.69
<unused3>
0.68
<unused23>
0.68
[@BOS@]
0.68
<pad>
0.68
Activations Density 0.539%