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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and possessives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suivantes
    -0.62
     myſelf
    -0.60
     himſelf
    -0.60
     itſelf
    -0.59
    WebServlet
    -0.59
    נטרנט
    -0.59
    ترنت
    -0.59
     tijden
    -0.58
     econó
    -0.58
     themſelves
    -0.57
    POSITIVE LOGITS
    PreferredItem
    0.78
     own
    0.77
     his
    0.75
    是我的
    0.73
     His
    0.72
     HIS
    0.71
    Whose
    0.71
    itoneal
    0.69
    jspx
    0.69
     their
    0.67
    Act Density 0.325%

    No Known Activations