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

    Neuronpedia

    INDEX
    Explanations

    mentions of the United States (US)

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceFile
    -0.77
    bably
    -0.72
    inately
    -0.70
    idates
    -0.68
    È
    -0.67
    ients
    -0.67
    rette
    -0.66
     Kard
    -0.65
     Adin
    -0.65
    antly
    -0.65
    POSITIVE LOGITS
     embassy
    1.09
     Embassy
    1.06
    AAF
    1.04
     ambassador
    0.84
    ADA
    0.83
     Dollar
    0.82
     Ambassador
    0.80
     Presidential
    0.80
     embassies
    0.80
     Army
    0.79
    Act Density 0.038%

    No Known Activations