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

    Neuronpedia

    INDEX
    Explanations

    dates written in the format "ordinal number (e.g., 4th) followed by the month"

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical references to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opolis
    -0.71
    theless
    -0.69
    uploads
    -0.62
    Shares
    -0.59
    TABLE
    -0.58
     toget
    -0.58
    packed
    -0.58
    1920
    -0.57
    require
    -0.56
    ctrl
    -0.56
    POSITIVE LOGITS
     onwards
    0.76
    imester
    0.74
    endment
    0.72
    eve
    0.68
    rollers
    0.68
    姫
    0.64
    ancers
    0.64
    oor
    0.64
    cember
    0.61
    å°Ĩ
    0.60
    Act Density 0.193%

    No Known Activations