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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or paragraphs in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ไร
    -0.46
     sere
    -0.45
     …
    -0.44
    formaz
    -0.44
    estine
    -0.44
    میل
    -0.42
    itsi
    -0.41
    fjspx
    -0.41
    도
    -0.41
     Pack
    -0.41
    POSITIVE LOGITS
    <bos>
    0.88
    ArgsConstructor
    0.72
    //
    0.68
     nargin
    0.67
    PhysRevD
    0.67
     rehearing
    0.64
    TintMode
    0.64
    droje
    0.64
    numerusform
    0.62
    vaadin
    0.61
    Act Density 0.033%

    No Known Activations