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

    Neuronpedia

    INDEX
    Explanations

    references to celebrities and their influence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.18
    ners
    -0.17
    adora
    -0.17
    елов
    -0.16
    onya
    -0.16
    adoras
    -0.15
    yonel
    -0.15
    ayo
    -0.15
    omo
    -0.15
    quet
    -0.15
    POSITIVE LOGITS
    brities
    0.17
    ved
    0.16
    ized
    0.16
    473
    0.15
    odd
    0.15
     odd
    0.15
     crushing
    0.15
     chef
    0.14
    hood
    0.14
    YN
    0.14
    Act Density 0.019%

    No Known Activations