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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically the name "Knight" with variations in numerical values

    oai_token-act-pair · gpt-3.5-turbo

    references to a character named Knight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obos
    -0.73
    pty
    -0.72
    ential
    -0.71
    andem
    -0.71
    posium
    -0.71
    istors
    -0.70
    ional
    -0.70
    eph
    -0.67
    imester
    -0.67
    istor
    -0.66
    POSITIVE LOGITS
     Knight
    1.23
     Templar
    1.20
    mare
    1.13
    mares
    1.04
    holder
    1.01
     Knights
    0.88
     Templ
    0.88
     knight
    0.86
     Rider
    0.85
    Knight
    0.85
    Act Density 0.009%

    No Known Activations