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

    Neuronpedia

    INDEX
    Explanations

    references to social or economic marginalization

    oai_token-act-pair · gpt-3.5-turbo

    references to marginalization and specific individuals related to political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aird
    -0.82
    sterdam
    -0.80
    enegger
    -0.79
    edom
    -0.71
    perture
    -0.69
    ily
    -0.69
    creen
    -0.67
    abba
    -0.67
    yne
    -0.67
    atcher
    -0.64
    POSITIVE LOGITS
    osaurs
    0.86
    iously
    0.83
    vill
    0.77
    bed
    0.76
    itic
    0.75
    ius
    0.73
    culosis
    0.73
    rics
    0.73
    Marginal
    0.71
    ocl
    0.71
    Act Density 0.075%

    No Known Activations