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

    Neuronpedia

    INDEX
    Explanations

    direct quotations and speech markers in the text

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

    Text enclosed in quotation marks

    np_acts-logits-general · gemini-2.0-flash

    quoted speech contents

    np_acts-logits-general · gemini-2.5-flash-lite

    the start of direct quoted speech in attributed statements, especially opening quotation marks and the surrounding speech-attribution context.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.90
     تضيفلها
    -0.77
    Vidite
    -0.75
    fromnode
    -0.75
    -0.73
     propOrder
    -0.71
    ๣
    -0.69
     مرئيه
    -0.69
    -0.69
     queſto
    -0.67
    POSITIVE LOGITS
    “
    0.56
    I
    0.47
    If
    0.43
    This
    0.40
    The
    0.40
    When
    0.40
    We
    0.40
     Inscrivez
    0.39
    It
    0.39
     "
    0.36
    Act Density 0.092%

    No Known Activations