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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and formatting elements in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IRM
    -0.17
    peare
    -0.15
     Merchant
    -0.14
    ially
    -0.14
    ERM
    -0.14
    utenberg
    -0.14
    .RunWith
    -0.14
    ÑĢаж
    -0.14
    filled
    -0.14
    à¹īา
    -0.14
    POSITIVE LOGITS
     Bliss
    0.16
    arer
    0.15
     SM
    0.14
    IID
    0.14
    UNCH
    0.13
    ocaly
    0.13
     Foley
    0.13
     ³³ ³³ ³³ ³³
    0.13
    oris
    0.13
    -picture
    0.13
    Act Density 0.057%

    No Known Activations