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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal citizenship status and related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of citizenship and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovie
    -0.74
    erman
    -0.71
    err
    -0.71
     Vaj
    -0.70
    EMS
    -0.68
     Winc
    -0.66
    aster
    -0.64
    oths
    -0.64
    arg
    -0.63
    hiba
    -0.63
    POSITIVE LOGITS
     citizenship
    1.22
     Citizenship
    0.99
     revocation
    0.82
    worthiness
    0.82
    ilege
    0.82
    ignt
    0.81
     versa
    0.80
     honors
    0.80
     abroad
    0.80
     eligibility
    0.78
    Act Density 0.011%

    No Known Activations