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

    Neuronpedia

    INDEX
    Explanations

    words related to positions of authority and roles in organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igm
    -0.15
    Ñĸон
    -0.15
     sẵn
    -0.15
     çev
    -0.15
    383
    -0.14
    alu
    -0.14
    angs
    -0.14
    itor
    -0.14
    sky
    -0.13
     Levy
    -0.13
    POSITIVE LOGITS
    HECK
    0.15
    ç«ł
    0.15
    ippo
    0.15
     onBackPressed
    0.15
    using
    0.14
    ży
    0.14
    antino
    0.14
     kra
    0.14
    ancock
    0.14
    ordo
    0.13
    Act Density 0.540%

    No Known Activations