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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies and research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uros
    -0.14
    ounding
    -0.14
     wrest
    -0.14
    ainless
    -0.14
     to
    -0.14
    Leod
    -0.14
     other
    -0.13
     &
    -0.13
    rah
    -0.13
    ante
    -0.13
    POSITIVE LOGITS
    mpar
    0.17
    μιο
    0.17
    deniz
    0.16
     attent
    0.16
    edl
    0.15
    .ads
    0.15
    iddi
    0.14
     derec
    0.14
    Sharper
    0.14
    /Library
    0.14
    Act Density 0.053%

    No Known Activations