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

    Neuronpedia

    INDEX
    Explanations

    names of specific countries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of countries and specific geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onym
    -0.69
    endum
    -0.68
    tk
    -0.68
    sense
    -0.68
    odox
    -0.67
    adobe
    -0.67
    lopp
    -0.65
    atin
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.63
    milo
    -0.62
    POSITIVE LOGITS
     respectively
    1.53
     alike
    1.38
     combined
    0.95
     coasts
    0.93
     Empires
    0.87
     campuses
    0.85
     economies
    0.84
     sectors
    0.84
     realms
    0.80
     markets
    0.79
    Act Density 0.189%

    No Known Activations