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

    Neuronpedia

    INDEX
    Explanations

    references to attribution in academic and licensing contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oden
    -0.18
    endon
    -0.18
    ushman
    -0.16
    èĴ
    -0.15
    ÙĨد
    -0.15
    iten
    -0.15
    eden
    -0.14
    æ°¸ä¹ħ
    -0.14
    chants
    -0.14
     jack
    -0.14
    POSITIVE LOGITS
    ITLE
    0.17
    .ops
    0.15
    tpl
    0.15
    imb
    0.15
    tea
    0.15
    iou
    0.15
    allery
    0.15
     пÑĢид
    0.15
    ÛĮ
    0.14
    tiv
    0.14
    Act Density 0.002%

    No Known Activations