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

    Neuronpedia

    INDEX
    Explanations

    mentions of things making a comeback

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "comeback."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -1.08
    avery
    -0.85
    Irish
    -0.72
    ģ
    -0.72
    aves
    -0.71
    bis
    -0.70
    acht
    -0.70
    agram
    -0.66
    ETA
    -0.65
    autical
    -0.65
    POSITIVE LOGITS
     comeback
    1.09
    wcs
    0.82
     shenan
    0.71
    spective
    0.71
    ilee
    0.70
     resurgence
    0.69
    roads
    0.66
    prise
    0.66
    ilitation
    0.65
    ilitating
    0.65
    Act Density 0.013%

    No Known Activations