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

    Neuronpedia

    INDEX
    Explanations

    mentions of various nationalities or ethnicities

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate nationalities or regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.77
    Denver
    -0.76
    ods
    -0.74
    ENN
    -0.74
    Toronto
    -0.74
    Kelly
    -0.70
    Wisconsin
    -0.70
    asonable
    -0.70
    ucl
    -0.69
    lished
    -0.69
    POSITIVE LOGITS
    istan
    1.28
     Airways
    1.14
     Airlines
    1.07
     Nadu
    1.02
    ese
    1.00
     proverb
    0.94
     Islands
    0.93
     Embassy
    0.92
    ican
    0.89
     embassy
    0.89
    Act Density 0.126%

    No Known Activations