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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or prerequisites before taking action

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    GeneratedCode
    -0.68
    SuppressLint
    -0.66
    AndEndTag
    -0.61
    GEBURTSDATUM
    -0.59
    elsif
    -0.53
     lccn
    -0.52
     ویکی‌پدی
    -0.49
    BindView
    -0.49
    rzost
    -0.49
    printStackTrace
    -0.49
    POSITIVE LOGITS
    paravant
    0.77
    Sebelum
    0.69
     Sebelum
    0.66
     CURIAM
    0.65
     voordat
    0.64
     sauvages
    0.64
    Sebelumnya
    0.61
     étoit
    0.61
     pouvoit
    0.59
    ्रीय
    0.58
    Act Density 0.014%

    No Known Activations