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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "any" is used in a variety of contexts within the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "any" and similar contextual uses indicating inclusivity or generality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rex
    -0.71
    seless
    -0.71
    endas
    -0.67
    bows
    -0.63
    ly
    -0.62
    ros
    -0.61
    rez
    -0.61
    combe
    -0.61
    expensive
    -0.59
    ÃŁ
    -0.58
    POSITIVE LOGITS
    THING
    1.39
    body
    0.98
    WHERE
    0.95
    thin
    0.93
    where
    0.93
     conceivable
    0.91
     imaginable
    0.89
    ONE
    0.85
     kind
    0.80
     sort
    0.78
    Act Density 0.074%

    No Known Activations