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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ratios or proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yard
    -0.17
    eld
    -0.16
    unger
    -0.15
    们
    -0.15
    egg
    -0.15
    brush
    -0.14
    eg
    -0.14
    e
    -0.14
    elter
    -0.14
    inerary
    -0.14
    POSITIVE LOGITS
     annum
    0.22
     capita
    0.20
    iphery
    0.19
    elman
    0.19
    quisites
    0.19
    ipherals
    0.18
    missive
    0.18
    empt
    0.17
    pendicular
    0.16
    pend
    0.16
    Act Density 0.024%

    No Known Activations