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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "per" as it relates to quantities and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ships
    -0.18
    yard
    -0.17
    y
    -0.17
    ele
    -0.17
    e
    -0.16
    rzy
    -0.15
    ship
    -0.15
    ÑģÑĤÑİ
    -0.15
    sville
    -0.15
    eless
    -0.15
    POSITIVE LOGITS
     annum
    0.38
     capita
    0.32
    ipher
    0.26
    iphery
    0.26
    quisites
    0.24
    missive
    0.23
    cents
    0.23
     hour
    0.23
     week
    0.21
     month
    0.21
    Act Density 0.028%

    No Known Activations