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

    Neuronpedia

    INDEX
    Explanations

    words indicating superiority or excellence related to collaboration and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edin
    -0.16
    gan
    -0.16
     Sat
    -0.15
    ede
    -0.15
    ipher
    -0.15
     pier
    -0.14
    licit
    -0.14
    ucker
    -0.14
     Extreme
    -0.14
     deg
    -0.14
    POSITIVE LOGITS
    _PO
    0.14
    Ñİн
    0.14
    à¹ģà¸ķ
    0.14
    è¼Ķ
    0.14
    ÑĪÑĤов
    0.14
     worst
    0.13
     danmark
    0.13
     Crosby
    0.13
    ãĥĥãĥĦ
    0.13
     svens
    0.13
    Act Density 0.213%

    No Known Activations