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

    Neuronpedia

    INDEX
    Explanations

    references to historical and modern slavery, particularly focusing on the experiences of slaves themselves

    oai_token-act-pair · gpt-3.5-turbo

    references to slavery and the related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.80
    soType
    -0.74
     Bore
    -0.73
     Bie
    -0.71
     MacArthur
    -0.67
    colo
    -0.67
    OLOGY
    -0.66
     ellipt
    -0.66
    bsp
    -0.64
    ordan
    -0.64
    POSITIVE LOGITS
     slaves
    1.10
     slave
    1.07
    maid
    0.91
     enslaved
    0.86
     Leia
    0.86
     slavery
    0.85
    slave
    0.84
     Slave
    0.83
     plantation
    0.82
    holders
    0.81
    Act Density 0.013%

    No Known Activations