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

    Neuronpedia

    INDEX
    Explanations

    words related to manuscripts and publishing

    oai_token-act-pair · gpt-3.5-turbo

    references to manuscripts and their related elements, including publication status and issues like plagiarism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    evil
    -0.83
     Spears
    -0.75
    Ĭ±
    -0.73
    laws
    -0.73
    omer
    -0.71
    nie
    -0.70
    do
    -0.69
    ĪĴ
    -0.69
    lando
    -0.69
    ened
    -0.69
    POSITIVE LOGITS
     manuscript
    1.18
     manuscripts
    1.13
     conclud
    0.87
    uscript
    0.83
    smanship
    0.74
    ãĤ¼ãĤ¦ãĤ¹
    0.74
     guiActiveUn
    0.74
    lishing
    0.74
     handwritten
    0.73
    helm
    0.72
    Act Density 0.010%

    No Known Activations