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

    Neuronpedia

    INDEX
    Explanations

    words related to eligibility for programs, benefits, or scholarships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADER
    -0.18
    alice
    -0.16
    ucci
    -0.15
    phy
    -0.15
    аÑĢÑı
    -0.15
    ANJI
    -0.14
    closure
    -0.14
    umat
    -0.14
    uzzi
    -0.14
    à¸²à¸Ł
    -0.14
    POSITIVE LOGITS
    iele
    0.15
    281
    0.15
    MDB
    0.14
    embros
    0.14
    chten
    0.14
    imore
    0.14
    hlen
    0.14
    ĨĴ
    0.14
    upiter
    0.14
    //'
    0.14
    Act Density 0.003%

    No Known Activations