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

    Neuronpedia

    INDEX
    Explanations

    elements related to coding and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     form
    -0.14
    ”
    -0.13
    np
    -0.13
     too
    -0.13
    nonce
    -0.13
    jom
    -0.13
     and
    -0.13
     in
    -0.13
    ä¸İ
    -0.12
    owie
    -0.12
    POSITIVE LOGITS
    ,
    0.29
    Ù¬
    0.27
    ,%
    0.19
     ,
    0.18
     comma
    0.18
    ี,
    0.18
    ,...↵
    0.17
    [,
    0.17
    ,',
    0.16
    à¹Į,
    0.16
    Act Density 0.305%

    No Known Activations