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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "being."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llib
    -0.18
    MMdd
    -0.15
    quat
    -0.15
    yat
    -0.15
    esi
    -0.15
    /MIT
    -0.14
    inary
    -0.14
    onec
    -0.14
    ycz
    -0.14
    essian
    -0.14
    POSITIVE LOGITS
    COME
    0.18
    arded
    0.17
    fall
    0.17
    friend
    0.16
    chers
    0.16
    fits
    0.15
    ardless
    0.15
    eper
    0.15
     able
    0.14
    деÑĢ
    0.14
    Act Density 0.059%

    No Known Activations