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

    Neuronpedia

    INDEX
    Explanations

    references to male characters or subjects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     herself
    -0.77
     bint
    -0.73
    脚注の使い方
    -0.72
    protoimpl
    -0.66
    setVerticalGroup
    -0.66
    AccessorTable
    -0.63
    цезда
    -0.63
     Kaur
    -0.60
    Diweddarwch
    -0.57
    RefreshLayout
    -0.56
    POSITIVE LOGITS
     himself
    1.18
    himself
    1.03
     masculinity
    0.96
     manhood
    0.90
     masculino
    0.88
     male
    0.84
     Male
    0.84
     Males
    0.83
     męski
    0.82
     مردانه
    0.82
    Act Density 1.128%

    No Known Activations