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

    Neuronpedia

    INDEX
    Explanations

    nationalities and citizenships mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to different nationalities and citizenship status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tooth
    -0.75
    Nut
    -0.74
     Lans
    -0.74
    Prev
    -0.71
     Morning
    -0.69
    ww
    -0.69
     Hind
    -0.69
    SourceFile
    -0.67
    oco
    -0.65
    erella
    -0.65
    POSITIVE LOGITS
     abroad
    1.02
     residing
    1.00
     visas
    0.94
    hips
    0.87
     deported
    0.86
     extrad
    0.86
     fleeing
    0.85
     nationals
    0.84
     passports
    0.81
     overseas
    0.81
    Act Density 0.073%

    No Known Activations