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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics related to time and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NOW
    -0.15
     ruling
    -0.14
     now
    -0.14
    ZO
    -0.14
    etri
    -0.13
    uyến
    -0.13
    ante
    -0.13
     Heads
    -0.13
    wik
    -0.13
    uentes
    -0.13
    POSITIVE LOGITS
    ÅĽ
    0.15
    ÙĪرت
    0.15
    ë¹ĦìĬ¤
    0.15
     mimo
    0.15
    istrovstvÃŃ
    0.14
    endid
    0.14
    aln
    0.13
    _CLEAN
    0.13
    ypi
    0.13
    unken
    0.13
    Act Density 0.001%

    No Known Activations