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

    Neuronpedia

    INDEX
    Explanations

    references to prominent individuals or initials commonly associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ixed
    -0.15
    eger
    -0.15
    rio
    -0.15
    abouts
    -0.15
    dish
    -0.14
    igator
    -0.14
    εÏĢ
    -0.14
    BILE
    -0.14
    esting
    -0.14
     shit
    -0.14
    POSITIVE LOGITS
     Rowling
    0.17
    ész
    0.17
    ilim
    0.15
    morgan
    0.15
    esan
    0.15
    ivar
    0.15
     reim
    0.15
    iyim
    0.15
    bose
    0.14
    )did
    0.14
    Act Density 0.032%

    No Known Activations