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

    Neuronpedia

    INDEX
    Explanations

    references to male identities and roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     herself
    -1.02
     bint
    -0.84
    herself
    -0.72
    حياتها
    -0.68
     Kaur
    -0.65
    protoimpl
    -0.65
    脚注の使い方
    -0.64
     Arund
    -0.61
     могла
    -0.58
    цезда
    -0.57
    POSITIVE LOGITS
     himself
    1.26
    himself
    1.09
     masculinity
    0.98
     manhood
    0.97
     Himself
    0.87
     Males
    0.83
     مردانه
    0.82
     masculino
    0.82
     Male
    0.81
     męski
    0.81
    Act Density 1.158%

    No Known Activations