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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "regular" or its variants, indicating a focus on routine or consistency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollen
    -0.17
    chod
    -0.16
    guard
    -0.15
    chine
    -0.15
    elson
    -0.15
    jom
    -0.15
    gun
    -0.15
    cron
    -0.14
    Vien
    -0.14
    oge
    -0.14
    POSITIVE LOGITS
    ities
    0.25
    ity
    0.24
    mente
    0.23
    lah
    0.19
    s
    0.18
    ized
    0.18
    lies
    0.18
    ly
    0.18
    ily
    0.17
    sand
    0.17
    Act Density 0.049%

    No Known Activations