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

    Neuronpedia

    INDEX
    Explanations

    words associated with power dynamics and conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /from
    -0.17
    cente
    -0.14
    996
    -0.14
    ÄĽ
    -0.14
    avian
    -0.14
    quina
    -0.13
    ieber
    -0.13
    bih
    -0.13
     SqlDbType
    -0.13
    qualities
    -0.13
    POSITIVE LOGITS
    ing
    0.18
    ise
    0.17
    istically
    0.16
    izes
    0.15
    ivate
    0.15
    ises
    0.15
    erea
    0.14
    ed
    0.13
    ISE
    0.13
    mada
    0.13
    Act Density 0.228%

    No Known Activations