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

    Neuronpedia

    INDEX
    Explanations

    years or time periods

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of dates and numerical data related to events or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ©
    -0.69
    olded
    -0.67
    Ultimately
    -0.65
    "},"
    -0.62
    obook
    -0.62
     Finder
    -0.62
    rack
    -0.61
     Ultimately
    -0.61
    onica
    -0.60
    rium
    -0.60
    POSITIVE LOGITS
    since
    0.84
     since
    0.77
     hasn
    0.72
    has
    0.72
    ©¶æ¥µ
    0.70
     steadily
    0.70
     successive
    0.70
    lov
    0.67
     countless
    0.65
     ende
    0.63
    Act Density 0.191%

    No Known Activations