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

    Neuronpedia

    INDEX
    Explanations

    countries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adobe
    -0.67
    blem
    -0.66
    lopp
    -0.65
    multipl
    -0.64
    76561
    -0.64
    imb
    -0.64
    animate
    -0.63
    á½
    -0.62
    sense
    -0.62
    áµ
    -0.61
    POSITIVE LOGITS
     respectively
    1.44
     alike
    1.42
     combined
    0.79
     versa
    0.75
     Indies
    0.70
     Empires
    0.68
    aucuses
    0.66
    avia
    0.66
     coasts
    0.65
     cohorts
    0.65
    Act Density 0.167%

    No Known Activations