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

    Neuronpedia

    INDEX
    Explanations

    references to actions or processes related to data or experimental results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulpt
    -0.20
    å¼ı
    -0.16
    aight
    -0.15
    TRACE
    -0.15
    orte
    -0.14
    etten
    -0.14
    /Instruction
    -0.14
    arih
    -0.14
    idos
    -0.13
     ngu
    -0.13
    POSITIVE LOGITS
    pedia
    0.15
    Executor
    0.15
    illard
    0.15
    åĿĬ
    0.15
    Outlet
    0.15
    _sink
    0.14
     Pest
    0.14
     rapid
    0.14
    .toHexString
    0.14
     Fant
    0.13
    Act Density 0.158%

    No Known Activations