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

    Neuronpedia

    INDEX
    Explanations

    terms related to theft and extraction of various items

    oai_token-act-pair · gpt-3.5-turbo

    references to theft and illegal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clus
    -0.66
    anmar
    -0.57
     Leilan
    -0.54
     Countdown
    -0.54
     Inquisition
    -0.54
    athlon
    -0.53
    instein
    -0.53
    edIn
    -0.53
    acco
    -0.52
    phe
    -0.52
    POSITIVE LOGITS
     from
    1.28
     FROM
    1.15
    from
    1.14
     cheaply
    0.97
    From
    0.94
     From
    0.94
    ById
    0.92
    needed
    0.79
     offline
    0.75
     belonging
    0.71
    Act Density 0.493%

    No Known Activations