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

    Neuronpedia

    INDEX
    Explanations

    repetitions of the phrase "you know."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ddelweddau
    -0.71
     Roskov
    -0.69
     ModelExpression
    -0.65
    setDo
    -0.64
     ویکی‌پدیای
    -0.64
     avoient
    -0.63
    Smarty
    -0.62
     sembler
    -0.62
    ("-");
    -0.62
     Jefus
    -0.61
    POSITIVE LOGITS
     مشين
    0.67
    HomeAsUpEnabled
    0.64
     ho
    0.63
     know
    0.62
     like
    0.61
    onuclear
    0.57
    rego
    0.57
    målet
    0.56
     Greenberg
    0.55
    printStackTrace
    0.54
    Act Density 0.035%

    No Known Activations