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

    Neuronpedia

    INDEX
    Explanations

    text related to time periods

    oai_token-act-pair · gpt-3.5-turbo

    negative numerical values associated with durations or time spans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rica
    -0.75
     Dos
    -0.66
     Mara
    -0.64
     heights
    -0.64
     Thumbnails
    -0.64
     Illum
    -0.64
     Uncle
    -0.63
     Proc
    -0.63
     Glas
    -0.63
     Borders
    -0.63
    POSITIVE LOGITS
    minute
    1.46
    year
    1.46
    month
    1.43
    hour
    1.43
    million
    1.34
    member
    1.29
    second
    1.29
    mile
    1.28
    degree
    1.27
    percent
    1.26
    Act Density 0.079%

    No Known Activations