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

    Neuronpedia

    INDEX
    Explanations

    key terms and numerical data related to research results and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.77
     فريبيس
    -0.76
    BagLayout
    -0.69
    cửa
    -0.66
    nologue
    -0.65
     NSObject
    -0.64
    principalTable
    -0.64
    aarrggbb
    -0.63
    ########.
    -0.62
    ULDER
    -0.61
    POSITIVE LOGITS
    The
    0.82
    awtextra
    0.75
     The
    0.67
    When
    0.63
     meanwhile
    0.62
    This
    0.59
     natomiast
    0.58
    To
    0.57
    However
    0.56
    On
    0.55
    Act Density 0.317%

    No Known Activations