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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating improvement or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antom
    -0.15
    bin
    -0.15
    Lon
    -0.14
    legates
    -0.14
    quets
    -0.14
     bin
    -0.14
    lie
    -0.14
    embers
    -0.14
     Ãľst
    -0.14
    957
    -0.14
    POSITIVE LOGITS
    pread
    0.18
    arda
    0.16
     ado
    0.16
    odic
    0.15
     Mellon
    0.15
    ODEV
    0.14
    anza
    0.14
    opers
    0.14
    ikel
    0.14
    zac
    0.14
    Act Density 0.047%

    No Known Activations