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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms indicating support or accompaniment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apons
    -0.17
    eger
    -0.17
    ylland
    -0.17
    bies
    -0.16
    onomy
    -0.16
    fty
    -0.16
    born
    -0.16
    ched
    -0.16
    agar
    -0.15
    .VideoCapture
    -0.15
    POSITIVE LOGITS
    ouflage
    0.16
    modation
    0.16
    ately
    0.16
    /support
    0.14
    als
    0.14
    arily
    0.14
    RequestId
    0.14
    dess
    0.14
    éļ¨
    0.14
    ments
    0.14
    Act Density 0.026%

    No Known Activations