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

    Neuronpedia

    INDEX
    Explanations

    references to gender dynamics and societal roles in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.77
    脚注の使い方
    -0.69
    setVerticalGroup
    -0.64
     صوتيه
    -0.63
    UnsafeEnabled
    -0.61
    `{.
    -0.58
    спери
    -0.57
     Biss
    -0.55
     snippetHide
    -0.55
    μον
    -0.55
    POSITIVE LOGITS
     male
    0.94
     women
    0.93
     masculine
    0.92
     Women
    0.89
     Mascul
    0.88
     masculinity
    0.88
     mascul
    0.87
     Male
    0.86
    Male
    0.85
     manly
    0.85
    Act Density 0.356%

    No Known Activations