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

    Neuronpedia

    INDEX
    Explanations

    numbers, dates, and monetary values in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    references to dates, times, and specific events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.37
    natureconservancy
    -0.34
    ĵĺ
    -0.32
    âķIJâķIJ
    -0.31
     welf
    -0.31
    Digital
    -0.31
     skelet
    -0.30
    ACP
    -0.30
    adem
    -0.29
     Pv
    -0.29
    POSITIVE LOGITS
    iversary
    0.44
    nesday
    0.43
    edin
    0.39
    ividual
    0.38
    igible
    0.36
    代
    0.36
     lasts
    0.35
    tenance
    0.35
    isphere
    0.35
    mite
    0.35
    Act Density 0.952%

    No Known Activations