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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orro
    -0.16
    esome
    -0.15
    etten
    -0.14
    еÑģп
    -0.14
    idges
    -0.14
     sco
    -0.14
    ampler
    -0.14
    lei
    -0.13
    oun
    -0.13
     incur
    -0.13
    POSITIVE LOGITS
    ầm
    0.17
    holm
    0.17
    unte
    0.16
    tha
    0.15
    761
    0.14
    unta
    0.14
    맥
    0.14
    osen
    0.14
    ìĿ´íĦ°
    0.14
    mouth
    0.14
    Act Density 0.063%

    No Known Activations