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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns ('he', 'him', 'his', 'she', 'her') referring to individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to male pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.62
     Articles
    -0.62
    اÙĦ
    -0.58
    Services
    -0.57
    change
    -0.56
     Actress
    -0.56
     Communications
    -0.56
     Addiction
    -0.55
     Clintons
    -0.55
    isSpecialOrderable
    -0.55
    POSITIVE LOGITS
     Majesty
    1.04
    panic
    1.00
    uristic
    0.92
    reditary
    0.91
    /
    0.88
    mos
    0.79
    ures
    0.79
    sing
    0.78
    eding
    0.77
    bert
    0.75
    Act Density 0.404%

    No Known Activations