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

    Neuronpedia

    INDEX
    Explanations

    references to gender, specifically focusing on male and female entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antaranya
    -0.52
    AnchorStyles
    -0.50
     abbraccio
    -0.47
    styleable
    -0.46
    WebServlet
    -0.45
    verifyException
    -0.45
    SBATCH
    -0.45
    irvana
    -0.45
    geddon
    -0.44
     inning
    -0.44
    POSITIVE LOGITS
     male
    3.63
    Male
    3.23
     Male
    3.22
    male
    3.08
     MALE
    2.91
    MALE
    2.66
     female
    2.55
    Female
    2.44
     Female
    2.42
     males
    2.41
    Act Density 0.237%

    No Known Activations