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

    Neuronpedia

    INDEX
    Explanations

    words related to time, such as "weeks", "days", "hours", and "months"

    oai_token-act-pair · gpt-3.5-turbo

    references to time-related concepts, particularly focusing on finality and significant days or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lys
    -0.68
    uan
    -0.64
    urat
    -0.61
    utical
    -0.60
    Hor
    -0.60
     Specifically
    -0.59
    arrass
    -0.58
     anecd
    -0.57
    oman
    -0.56
     Inqu
    -0.56
    POSITIVE LOGITS
    imester
    0.91
     bidder
    0.78
    *)
    0.68
    sec
    0.68
    govtrack
    0.66
    antle
    0.66
     hurdle
    0.64
     vo
    0.63
    mony
    0.60
    imus
    0.60
    Act Density 0.116%

    No Known Activations