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

    Neuronpedia

    INDEX
    Explanations

    terms related to slavery and employment relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    employer, owner, landlord

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.50
    arrer
    -0.50
     Pip
    -0.49
    residents
    -0.49
    detti
    -0.49
    reprodu
    -0.48
    ilibrium
    -0.47
     ویکی‌پدی
    -0.47
    Esper
    -0.47
    Ais
    -0.47
    POSITIVE LOGITS
     employers
    0.84
     Arbeitgeber
    0.79
     employer
    0.78
    Employers
    0.73
     Employers
    0.73
     Employer
    0.69
    Employer
    0.69
     landlords
    0.68
     landlord
    0.68
     atasan
    0.66
    Act Density 0.052%

    No Known Activations