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

    Neuronpedia

    INDEX
    Explanations

    words related to political figures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the comma punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olars
    -0.71
    acters
    -0.69
    ocial
    -0.66
    versive
    -0.65
    eals
    -0.65
    isers
    -0.65
    inner
    -0.62
    atlantic
    -0.62
    ictional
    -0.61
     offender
    -0.61
    POSITIVE LOGITS
    76561
    0.81
     Jr
    0.77
    paio
    0.75
     aka
    0.72
    ĪĴ
    0.68
    ucci
    0.67
     Kard
    0.67
     etc
    0.66
     Baird
    0.65
     Sr
    0.65
    Act Density 0.175%

    No Known Activations