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

    Neuronpedia

    INDEX
    Explanations

    the word "do" when it is paired with a negation like "nothing to do with" indicating lack of association

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack of connection or relevance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pu
    -0.75
    don
    -0.70
    Reviewer
    -0.69
    imaru
    -0.66
    lake
    -0.65
    DOC
    -0.65
    taboola
    -0.64
    mu
    -0.64
    wagen
    -0.63
    pret
    -0.61
    POSITIVE LOGITS
    omsday
    0.75
    ozy
    0.72
    atives
    0.70
     entail
    0.67
    uate
    0.67
    actic
    0.66
     administr
    0.66
    pez
    0.65
    VIDIA
    0.65
     SEO
    0.64
    Act Density 0.038%

    No Known Activations