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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by specific keywords or phrases

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.61
    feed
    -0.59
    amaru
    -0.59
    atown
    -0.59
    atem
    -0.59
    actionDate
    -0.59
     jerk
    -0.58
     Jagu
    -0.58
    plin
    -0.57
    feature
    -0.57
    POSITIVE LOGITS
    th
    1.22
     months
    1.02
     percent
    0.94
    teenth
    0.94
    teen
    0.94
    71
    0.94
    een
    0.93
    ½
    0.93
    %
    0.93
     years
    0.92
    Act Density 0.243%

    No Known Activations