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

    Neuronpedia

    INDEX
    Explanations

    dates or time-related information presented in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly dates and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.72
    ogens
    -0.67
    Reviewer
    -0.67
    idad
    -0.64
    istries
    -0.64
    iann
    -0.63
    ibel
    -0.62
    DragonMagazine
    -0.61
    alion
    -0.60
    é¾įåĸļ士
    -0.60
    POSITIVE LOGITS
     rows
    0.68
    50
    0.61
     Cla
    0.60
     Grav
    0.60
    enda
    0.60
     Elliot
    0.59
    Skip
    0.58
    atin
    0.58
     Cassidy
    0.58
     Cecil
    0.57
    Act Density 0.200%

    No Known Activations