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

    Neuronpedia

    INDEX
    Explanations

    repetitive mentions of the word "all."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     all
    -0.27
     모ëijIJ
    -0.23
     вÑģе
    -0.21
     wszyst
    -0.18
    emens
    -0.18
    offee
    -0.17
    leitung
    -0.17
     ÏĮλα
    -0.16
    dz
    -0.16
    æīĢæľī
    -0.16
    POSITIVE LOGITS
    igator
    0.36
    uded
    0.35
    uring
    0.32
    igators
    0.30
    uding
    0.30
    urement
    0.30
    ready
    0.29
     sorts
    0.28
    oted
    0.28
    iteration
    0.28
    Act Density 0.216%

    No Known Activations