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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases starting with parentheses, potentially related to technical or specific information within a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses and their contents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tears
    -0.69
     distingu
    -0.69
     oranges
    -0.68
     vom
    -0.65
     Bris
    -0.64
     sadly
    -0.64
     flats
    -0.64
     accomp
    -0.63
     kindly
    -0.63
     looms
    -0.62
    POSITIVE LOGITS
    yet
    1.09
    sounding
    1.08
    albeit
    0.98
    non
    0.93
    atomic
    0.91
    meaning
    0.84
    anti
    0.82
    sic
    0.82
    but
    0.81
    enough
    0.81
    Act Density 0.247%

    No Known Activations