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

    Neuronpedia

    INDEX
    Explanations

    references to time measurements expressed in hours or physical measurements like feet, yards, and meters

    oai_token-act-pair · gpt-3.5-turbo

    units of measurement and time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    worldly
    -0.91
    icial
    -0.65
    anski
    -0.61
    ĸļ
    -0.57
    eering
    -0.57
    isy
    -0.57
    perse
    -0.56
    pic
    -0.56
    actionDate
    -0.56
    born
    -0.56
    POSITIVE LOGITS
    +)
    0.98
    +.
    0.91
    +,
    0.89
    +
    0.82
    plus
    0.78
     hindsight
    0.74
     apiece
    0.72
     increments
    0.71
     percentile
    0.70
     Anniversary
    0.70
    Act Density 0.228%

    No Known Activations