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

    Neuronpedia

    INDEX
    Explanations

    negative impacts and declines in quality or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ushing
    -0.18
     Vers
    -0.17
    Vers
    -0.16
    ÑĢаниÑĨ
    -0.14
    Ã
    -0.14
    DST
    -0.14
    gression
    -0.14
    øre
    -0.14
     FixedUpdate
    -0.14
     Pla
    -0.13
    POSITIVE LOGITS
     denen
    0.15
    erap
    0.15
    linger
    0.14
     vain
    0.13
    ainen
    0.13
    uae
    0.13
    alam
    0.13
    uais
    0.13
     distur
    0.12
     ac
    0.12
    Act Density 0.671%

    No Known Activations