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

    Neuronpedia

    INDEX
    Explanations

    information related to citizenship, immigration, and travel documents

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    essen
    -0.80
    Measure
    -0.78
     Winc
    -0.77
    leys
    -0.76
    EMS
    -0.75
    urgical
    -0.74
    enth
    -0.73
    MET
    -0.71
     WATCHED
    -0.71
    thora
    -0.69
    POSITIVE LOGITS
     visas
    1.26
     visa
    1.24
     citizenship
    1.17
     passports
    1.09
     versa
    1.04
     passport
    1.04
     deported
    1.00
     revocation
    0.95
     Citizenship
    0.93
     eligibility
    0.89
    Act Density 10.527%

    No Known Activations