INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.75
    LookAnd
    -0.69
     pitä
    -0.65
     étoient
    -0.64
     degrés
    -0.62
     leçon
    -0.60
     câbles
    -0.59
     spéciaux
    -0.57
     kautta
    -0.57
     avoient
    -0.57
    POSITIVE LOGITS
     your
    0.63
     it
    0.63
     new
    0.62
    cher
    0.59
     global
    0.57
    AsStream
    0.57
     life
    0.56
     raw
    0.55
     but
    0.55
     political
    0.53
    Act Density 0.003%

    No Known Activations