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

    Neuronpedia

    INDEX
    Explanations

    the acronym "Da" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Da" and its variations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburgh
    -1.13
    ãĤ¡
    -0.83
    LESS
    -0.82
    sburg
    -0.76
    ORED
    -0.76
    lessly
    -0.75
    ship
    -0.75
    MENT
    -0.73
    ï¸ı
    -0.72
    ships
    -0.71
    POSITIVE LOGITS
    isy
    1.15
    ft
    1.08
    pling
    0.94
    emon
    0.94
    fts
    0.89
    uman
    0.86
    ivari
    0.85
    emonic
    0.85
    qu
    0.83
    uthor
    0.83
    Act Density 0.014%

    No Known Activations