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

    Neuronpedia

    INDEX
    Explanations

    specific titles and terms related to cultural or creative works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urch
    -0.15
     activation
    -0.15
    imson
    -0.14
    алов
    -0.14
     Nam
    -0.14
    CHAN
    -0.14
    illy
    -0.14
     Agents
    -0.13
    pora
    -0.13
    uhan
    -0.13
    POSITIVE LOGITS
    quarters
    0.15
    iban
    0.14
    stakes
    0.14
    olean
    0.14
    ocked
    0.14
    perature
    0.14
    /Dk
    0.14
    (æľ¨
    0.14
    pared
    0.14
     Ïħ
    0.14
    Act Density 0.044%

    No Known Activations