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

    Neuronpedia

    INDEX
    Explanations

    references to factors influencing specific outcomes or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coming
    -0.21
    tim
    -0.19
    ernet
    -0.19
    ee
    -0.18
    ness
    -0.17
    946
    -0.17
    ough
    -0.17
    ongyang
    -0.17
    eltas
    -0.16
    esy
    -0.16
    POSITIVE LOGITS
    ials
    0.23
    ization
    0.23
    ially
    0.21
    ial
    0.20
    IAL
    0.19
    izations
    0.17
    UA
    0.17
    bilt
    0.16
    reon
    0.15
    apult
    0.15
    Act Density 0.023%

    No Known Activations