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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rights and legal protections

    oai_token-act-pair · gpt-3.5-turbo

    references to rights and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    trap
    -0.78
    wcsstore
    -0.75
    around
    -0.68
     certs
    -0.66
    staff
    -0.65
    BALL
    -0.62
    fml
    -0.61
    uality
    -0.61
    orie
    -0.60
     cocktails
    -0.59
    POSITIVE LOGITS
     citizens
    0.80
     conscience
    0.78
     minorities
    0.78
     peoples
    0.77
     individuals
    0.77
     landowners
    0.77
     citizenship
    0.76
    oso
    0.76
     persons
    0.74
    ividual
    0.74
    Act Density 0.089%

    No Known Activations