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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "man" or masculine figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ']")
    -0.95
    ^(@)
    -0.95
     للمعارف
    -0.92
    $.
    -0.88
    ","","
    -0.87
    BibitemShut
    -0.87
    "]);
    -0.86
    "])
    -0.85
    piac
    -0.84
    ']").
    -0.84
    POSITIVE LOGITS
     man
    1.76
     Man
    1.72
    Man
    1.59
     MAN
    1.51
    man
    1.50
     woman
    1.31
    MAN
    1.27
     mans
    1.20
     Woman
    1.17
     men
    1.17
    Act Density 0.081%

    No Known Activations