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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities, particularly related to people or brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vetica
    -0.17
    rew
    -0.15
    оваÑĢ
    -0.15
    istrovstvÃŃ
    -0.15
    aybe
    -0.14
    ัà¸Ļà¸ĺ
    -0.14
    raya
    -0.14
    ulary
    -0.14
    urnal
    -0.13
     Aires
    -0.13
    POSITIVE LOGITS
    viso
    0.18
    åĽ´
    0.16
    izin
    0.16
    ied
    0.15
    icz
    0.14
    ukkan
    0.14
    ecess
    0.14
    etik
    0.14
    afia
    0.14
     Î¥ÏĢο
    0.14
    Act Density 0.010%

    No Known Activations