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

    Neuronpedia

    INDEX
    Explanations

    references to groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to "people."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.74
    Va
    -0.72
    BALL
    -0.71
    illus
    -0.70
    Pg
    -0.69
    PET
    -0.67
    èª
    -0.66
    \/\/
    -0.66
    ategor
    -0.66
    yson
    -0.65
    POSITIVE LOGITS
     smugglers
    1.05
    liest
    1.03
    folk
    0.93
     inhab
    0.82
    ourced
    0.80
    hood
    0.78
     closest
    0.71
     traffickers
    0.70
     smugg
    0.70
     composing
    0.69
    Act Density 0.051%

    No Known Activations