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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cleaning or organizing spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undler
    -0.17
    isty
    -0.16
    esters
    -0.16
    lü
    -0.15
    ecal
    -0.15
    unas
    -0.15
    imits
    -0.15
    quette
    -0.14
    t
    -0.14
    ingle
    -0.14
    POSITIVE LOGITS
    /down
    0.28
    datable
    0.25
    pers
    0.23
    ping
    0.21
    shot
    0.19
    DATES
    0.19
    gradable
    0.19
    wards
    0.19
    datetime
    0.19
    dater
    0.18
    Act Density 0.159%

    No Known Activations