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

    Neuronpedia

    INDEX
    Explanations

    references to sourced information and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑģÑĤÑĢи
    -0.15
    SSI
    -0.15
    erras
    -0.15
    XX
    -0.15
    steen
    -0.14
    rell
    -0.14
    aron
    -0.14
    iesta
    -0.14
    енÑĮ
    -0.14
    gre
    -0.14
    POSITIVE LOGITS
    alim
    0.16
    _Tis
    0.15
    oho
    0.15
    æĥł
    0.14
    undles
    0.14
    |RF
    0.14
    idable
    0.14
    è§ī
    0.14
     имÑĥ
    0.14
    dbus
    0.13
    Act Density 0.109%

    No Known Activations