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

    Neuronpedia

    INDEX
    Explanations

    references to the term "woman," specifically focusing on variations of the word such as "woman," "women," and "womanhood."

    oai_token-act-pair · gpt-3.5-turbo

    words related to "man" or "woman."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REE
    -0.75
     Emin
    -0.65
    Delete
    -0.64
    urus
    -0.63
    ll
    -0.61
    UV
    -0.61
    ree
    -0.60
    DNA
    -0.59
    Haw
    -0.59
    holes
    -0.57
    POSITIVE LOGITS
    ufact
    1.36
    ia
    0.91
    yrinth
    0.88
    iak
    0.85
    icz
    0.83
    oman
    0.83
    ipolar
    0.82
    agement
    0.81
    ipal
    0.81
    isations
    0.81
    Act Density 0.042%

    No Known Activations