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

    Neuronpedia

    INDEX
    Explanations

    mentions of or references to "foreigners."

    oai_token-act-pair · gpt-3.5-turbo

    references to foreigners or foreign individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pton
    -0.71
    Adams
    -0.70
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.70
    apple
    -0.70
    phasis
    -0.67
     Fulton
    -0.67
    rol
    -0.66
    Discussion
    -0.66
    ucc
    -0.65
    Board
    -0.65
    POSITIVE LOGITS
     abroad
    1.16
     foreigners
    1.10
     overseas
    0.94
     foreigner
    0.93
     nationals
    0.91
     versa
    0.87
     undes
    0.82
    istani
    0.79
     travellers
    0.78
     fug
    0.78
    Act Density 0.006%

    No Known Activations