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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to the speaker or the audience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    pronouns and possessives in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inite
    -0.40
     hint
    -0.39
    HttpEntity
    -0.39
    一定的
    -0.38
    petual
    -0.37
    erty
    -0.36
    /**
    -0.36
    ただの
    -0.36
    AddHtmlAttribute
    -0.35
     aanv
    -0.35
    POSITIVE LOGITS
    我们
    1.02
    我們
    0.98
     我们
    0.91
    他們
    0.86
     우리
    0.79
    Mereka
    0.79
    他们
    0.79
    mereka
    0.77
    Мы
    0.77
     mereka
    0.75
    Act Density 0.004%

    No Known Activations