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

    Neuronpedia

    INDEX
    Explanations

    references to publications and reports, particularly those with dates and authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uckle
    -0.15
    acman
    -0.15
    bakan
    -0.15
    .uk
    -0.14
    uela
    -0.14
    SSIP
    -0.14
    igli
    -0.14
     Nec
    -0.14
     tiers
    -0.14
    mares
    -0.14
    POSITIVE LOGITS
    Mirror
    0.17
     inputs
    0.16
     Jeh
    0.16
     Publish
    0.16
     Mirror
    0.16
    Times
    0.16
     Times
    0.15
    _mirror
    0.15
     TIMES
    0.15
    echa
    0.15
    Act Density 0.056%

    No Known Activations