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

    Neuronpedia

    INDEX
    Explanations

    calls to action related to clicking or navigating through content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.84
    发表于
    -0.81
    يكب
    -0.75
    Życiorys
    -0.75
    ########.
    -0.74
    ItemBackground
    -0.71
     المعيارى
    -0.71
    TypedDataSet
    -0.71
     يتيمه
    -0.70
    ^(@
    -0.69
    POSITIVE LOGITS
     button
    0.65
     scroll
    0.53
    button
    0.53
    lan
    0.52
     juges
    0.48
     clicking
    0.48
    setupUi
    0.47
     Scroll
    0.46
     Button
    0.45
    <bos>
    0.45
    Act Density 0.136%

    No Known Activations