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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical concepts and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amer
    -0.17
    toDouble
    -0.15
    errar
    -0.15
    esar
    -0.14
    eres
    -0.14
    owler
    -0.14
    esa
    -0.14
    napshot
    -0.14
    scaling
    -0.14
    uyá»ģn
    -0.13
    POSITIVE LOGITS
    DED
    0.16
    ded
    0.16
    umb
    0.15
    ders
    0.15
    jedn
    0.15
    fabric
    0.15
    ÌĢ
    0.15
    ler
    0.15
     McInt
    0.14
    vin
    0.14
    Act Density 0.016%

    No Known Activations