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

    Neuronpedia

    INDEX
    Explanations

    references to specific jobs or occupations, particularly domestic roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.92
    AxisAlignment
    -0.87
     demografica
    -0.77
    contentLoaded
    -0.74
     MainAxisSize
    -0.71
     évêque
    -0.68
    UnusedPrivate
    -0.67
    +#+#
    -0.67
     Majefty
    -0.66
    pexpr
    -0.66
    POSITIVE LOGITS
     servant
    0.94
     servants
    0.92
    maid
    0.85
     maid
    0.84
     worker
    0.84
     maids
    0.83
     clerk
    0.82
     staff
    0.80
     assistant
    0.79
    servant
    0.79
    Act Density 0.288%

    No Known Activations