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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific individuals and technical terms related to a context involving decision-making or votes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loff
    -0.15
    indows
    -0.15
    valuate
    -0.14
    ضÛĮ
    -0.14
    Fcn
    -0.14
     ì¦
    -0.14
    ymm
    -0.14
    valu
    -0.14
    anja
    -0.14
    emplates
    -0.14
    POSITIVE LOGITS
    voy
    0.15
    enant
    0.15
    /articles
    0.15
    itive
    0.14
    ited
    0.14
    hti
    0.14
    ovány
    0.14
     .
    0.14
    ala
    0.14
    rows
    0.13
    Act Density 0.001%

    No Known Activations