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

    Neuronpedia

    INDEX
    Explanations

    the presence of the document's start and structure indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مشين
    -0.60
     @"/
    -0.56
     ويكيميديا
    -0.56
    IntoConstraints
    -0.56
    таратура
    -0.52
    เภ
    -0.52
     InputDecoration
    -0.51
    oose
    -0.50
    rimento
    -0.49
     samenwerking
    -0.49
    POSITIVE LOGITS
     born
    0.83
     inherit
    0.75
     whom
    0.73
     grandchildren
    0.71
     birth
    0.67
     youngest
    0.67
     begotten
    0.67
    growing
    0.67
    whom
    0.65
    Growing
    0.65
    Act Density 0.237%

    No Known Activations