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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the notion of "best."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    üçük
    -0.17
    udeau
    -0.16
    dued
    -0.15
    оÑĤÑĢеб
    -0.15
    allet
    -0.15
    ála
    -0.15
    osed
    -0.15
    ned
    -0.15
    occan
    -0.15
    antu
    -0.14
    POSITIVE LOGITS
    ow
    0.23
    seller
    0.22
    owing
    0.22
    -selling
    0.22
    -known
    0.22
    -case
    0.20
    ows
    0.18
    تز
    0.17
    ever
    0.17
    -equipped
    0.17
    Act Density 0.049%

    No Known Activations