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

    Neuronpedia

    INDEX
    Explanations

    references to masculine pronouns and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -1.00
    GEBURTSDATUM
    -0.99
     disambiguazione
    -0.90
     nakalista
    -0.87
    expandindo
    -0.87
     autorytatywna
    -0.87
     المعيارى
    -0.85
    mybatisplus
    -0.83
     ویکی‌پدیای
    -0.81
    IntoConstraints
    -0.81
    POSITIVE LOGITS
     He
    1.53
    He
    1.43
     She
    0.99
    She
    0.88
    It
    0.83
    The
    0.83
     They
    0.82
     It
    0.78
    Ge
    0.74
    We
    0.72
    Act Density 0.067%

    No Known Activations