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

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent individuals, particularly political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.75
    footed
    -0.70
    tle
    -0.68
    drm
    -0.67
    draw
    -0.66
    Score
    -0.65
    emouth
    -0.65
     Stories
    -0.65
    ipop
    -0.64
    soType
    -0.62
    POSITIVE LOGITS
    ãĥĺ
    0.77
    ÃĽ
    0.70
    ा
    0.69
    à¨
    0.65
     embargo
    0.64
    ij士
    0.62
    ļéĨĴ
    0.60
    rand
    0.60
    afort
    0.59
    Ö¼
    0.58
    Act Density 0.181%

    No Known Activations