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

    Neuronpedia

    INDEX
    Explanations

    names of countries and cities

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations and country names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.63
    ciating
    -0.57
    20439
    -0.53
    é¾įåĸļ士
    -0.52
    nces
    -0.51
     spo
    -0.51
     BALL
    -0.51
    ounced
    -0.50
    gas
    -0.50
    blem
    -0.49
    POSITIVE LOGITS
     TBA
    0.68
    /*
    0.67
    inus
    0.61
    advertising
    0.59
    /
    0.59
    /**
    0.58
    >(
    0.57
    ];
    0.56
    >[
    0.55
     (%)
    0.54
    Act Density 0.168%

    No Known Activations