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

    Neuronpedia

    INDEX
    Explanations

    terms related to drivers and driving concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oses
    -0.16
    ary
    -0.16
    ilde
    -0.15
    ikes
    -0.14
    yl
    -0.14
    ayment
    -0.14
    ariat
    -0.14
    tes
    -0.14
    جÛĮ
    -0.14
    živ
    -0.14
    POSITIVE LOGITS
    /pass
    0.17
    haft
    0.16
    驶
    0.16
    .drive
    0.16
    erot
    0.16
    anten
    0.16
    zeug
    0.15
    ouver
    0.15
    ington
    0.15
    pent
    0.15
    Act Density 0.023%

    No Known Activations