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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the pronouns "I," "they," "he," "we," and "it" along with their associated verb forms

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

    I was, it was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.50
     démocr
    -0.46
     صوتيه
    -0.45
     ویکی‌پدیا
    -0.43
     chrétien
    -0.43
     Houſe
    -0.41
     traditionnel
    -0.40
    LOYEES
    -0.39
    viewDidLoad
    -0.39
     HomeController
    -0.39
    POSITIVE LOGITS
    ographics
    0.49
     addirittura
    0.49
    吓得
    0.47
     Wikimedijinoj
    0.46
     practically
    0.45
    Cringe
    0.45
    jooq
    0.45
     undermine
    0.42
     almost
    0.42
    思わず
    0.42
    Act Density 0.020%

    No Known Activations