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

    Neuronpedia

    INDEX
    Explanations

    titles or roles associated with individuals, particularly in formal or authoritative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeda
    -0.18
    upt
    -0.17
    ίγ
    -0.15
     titled
    -0.15
    imest
    -0.15
    ieber
    -0.14
     unnamed
    -0.14
    _GENER
    -0.14
    åı«
    -0.14
    -widget
    -0.14
    POSITIVE LOGITS
     who
    0.23
     whom
    0.22
     whose
    0.19
    who
    0.17
     from
    0.14
     nearest
    0.14
    gh
    0.14
    .k
    0.13
     himself
    0.13
    Ïģιά
    0.13
    Act Density 0.103%

    No Known Activations