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

    Neuronpedia

    INDEX
    Explanations

    references to weight measurements in pounds and kilograms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruz
    -0.18
    ạc
    -0.15
    ione
    -0.14
     mil
    -0.14
    udeau
    -0.14
    ürn
    -0.14
    urum
    -0.14
     grandson
    -0.14
    asin
    -0.13
    Mil
    -0.13
    POSITIVE LOGITS
    .scalablytyped
    0.20
    éĻĦ
    0.15
    åĢŁ
    0.15
     Rockefeller
    0.15
    monic
    0.14
    jk
    0.13
    otton
    0.13
    ίνη
    0.13
     nackte
    0.13
    mono
    0.13
    Act Density 0.013%

    No Known Activations