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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to positions or rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mess
    -0.15
    barang
    -0.15
    cus
    -0.14
    Mess
    -0.14
    ellen
    -0.14
    blur
    -0.14
    legg
    -0.14
    añ
    -0.14
    <$
    -0.14
    ritel
    -0.14
    POSITIVE LOGITS
    allery
    0.16
    uti
    0.16
    ä¼
    0.15
    uth
    0.15
    iaz
    0.15
    tery
    0.14
    plits
    0.14
    patibility
    0.14
    och
    0.14
    abet
    0.14
    Act Density 0.000%

    No Known Activations