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

    Neuronpedia

    INDEX
    Explanations

    Latin characters with diacritics

    oai_token-act-pair · gpt-3.5-turbo

    elements related to significant societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quet
    -0.67
    hent
    -0.63
    audi
    -0.61
    fac
    -0.61
    DragonMagazine
    -0.59
    arella
    -0.59
    quant
    -0.57
     CoC
    -0.57
    ppe
    -0.57
    dq
    -0.56
    POSITIVE LOGITS
    window
    0.94
    Loading
    0.88
    ................................................................
    0.70
    =-=-=-=-
    0.69
    WARNING
    0.67
    WASHINGTON
    0.64
    hyde
    0.64
    ãĤ¨ãĥ«
    0.64
     Kers
    0.62
    %%%%
    0.62
    Act Density 0.101%

    No Known Activations