Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     afirmó
    1.16
     envió
    1.03
     elevado
    0.98
     quería
    0.97
     mendukung
    0.97
     Não
    0.96
     quiere
    0.96
     nėra
    0.95
     findet
    0.95
     afirmou
    0.95
    POSITIVE LOGITS
     to
    0.70
    ه
    0.70
    i
    0.66
     in
    0.63
    LY
    0.61
     or
    0.61
     for
    0.60
    បញ្
    0.60
     accent
    0.59
    ی
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.