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

    Neuronpedia

    INDEX
    Explanations

    references to a specific entity named "Maid"

    oai_token-act-pair · gpt-3.5-turbo

    references to "maid" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.85
    ++++++++++++++++
    -0.82
    OPLE
    -0.76
    selection
    -0.71
    UNCH
    -0.69
    OPER
    -0.67
    utherford
    -0.66
    ogene
    -0.65
    =-=-=-=-
    -0.65
    REDACTED
    -0.62
    POSITIVE LOGITS
     Maid
    1.28
    maid
    0.90
    enium
    0.87
    ento
    0.85
    lets
    0.83
    iak
    0.82
    stones
    0.82
     maid
    0.80
    ens
    0.80
    ments
    0.79
    Act Density 0.007%

    No Known Activations