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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to female figures

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "lady" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CS
    -0.70
    Blocks
    -0.64
     Ratings
    -0.62
    ingu
    -0.61
     contiguous
    -0.61
     Hansen
    -0.60
    anks
    -0.59
    Applications
    -0.59
    keys
    -0.59
    casts
    -0.59
    POSITIVE LOGITS
     lady
    3.68
     ladies
    2.20
     Lady
    2.15
    Lady
    2.11
     woman
    1.88
     girl
    1.71
     gentleman
    1.70
    Woman
    1.64
    woman
    1.61
     Ladies
    1.50
    Act Density 0.013%

    No Known Activations