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

    Neuronpedia

    INDEX
    Explanations

    terms related to gender distribution and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BrowserModule
    -0.76
    Vidite
    -0.69
     Parigi
    -0.69
     المعيارى
    -0.69
    afficheront
    -0.68
    UnsafeEnabled
    -0.67
    الإنجليزية
    -0.67
     صوتيه
    -0.66
    atimes
    -0.65
    ❋
    -0.64
    POSITIVE LOGITS
     male
    1.36
     women
    1.20
    Male
    1.15
     Male
    1.14
     males
    1.13
    male
    1.09
     female
    1.09
     masculine
    1.05
     männ
    1.05
     Female
    1.02
    Act Density 0.234%

    No Known Activations