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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     are
    0.69
    ди
    0.64
    3
    0.63
    ми
    0.63
    কে
    0.59
    ۳
    0.59
    ль
    0.59
    َ
    0.57
     presidente
    0.57
     ovat
    0.56
    POSITIVE LOGITS
    ing
    0.59
    boks
    0.58
    b
    0.57
     इंतजार
    0.50
     வகையில்
    0.48
    partum
    0.48
     Nachdem
    0.47
     ATV
    0.46
    beli
    0.46
    brak
    0.46
    Act Density 3.752%

    No Known Activations