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

    Neuronpedia

    INDEX
    Explanations

    the name "Loretta" repeated in different contexts and variations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly those of public figures in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ergy
    -0.91
    shire
    -0.89
    eric
    -0.83
    er
    -0.78
    ships
    -0.76
    lich
    -0.75
    bies
    -0.74
    egg
    -0.73
    enstein
    -0.73
    spring
    -0.72
    POSITIVE LOGITS
    arnaev
    0.77
     fide
    0.74
    velength
    0.73
    ignt
    0.70
    BILITY
    0.69
    ĨĴ
    0.69
    Availability
    0.68
     Duty
    0.65
    utonium
    0.64
    ioxide
    0.64
    Act Density 0.032%

    No Known Activations