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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific geographical locations, with a focus on South Africa

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Mech
    -0.75
    hower
    -0.72
    PATH
    -0.66
    naissance
    -0.66
    laden
    -0.66
    romeda
    -0.65
     cumbers
    -0.63
    cru
    -0.63
    mares
    -0.62
    Sense
    -0.60
    POSITIVE LOGITS
    tein
    0.80
     Mandela
    0.78
     Polic
    0.73
     Telecom
    0.70
     Presbyterian
    0.67
    atoon
    0.66
    ADA
    0.66
     Broadcasting
    0.66
    istan
    0.64
    à¥
    0.64
    Act Density 0.064%

    No Known Activations