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

    Neuronpedia

    INDEX
    Explanations

    scientific references and citations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idth
    -0.15
    ambi
    -0.15
    rees
    -0.15
    ucha
    -0.15
    adece
    -0.15
    ëŁ
    -0.15
    ewan
    -0.15
     Záp
    -0.14
    Warm
    -0.14
     Warm
    -0.14
    POSITIVE LOGITS
    ç·Ĵ
    0.15
     Bav
    0.15
    124
    0.15
     apr
    0.14
    ä¸Ķ
    0.14
     fold
    0.14
    084
    0.13
    724
    0.13
    bih
    0.13
     Naz
    0.13
    Act Density 0.221%

    No Known Activations