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

    Neuronpedia

    INDEX
    Explanations

    specific numerical patterns

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and references to figures in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.76
    76561
    -0.66
    paralle
    -0.64
     Marathon
    -0.60
     defamation
    -0.59
    EngineDebug
    -0.59
     disqualified
    -0.57
    userc
    -0.56
     blinding
    -0.56
     disqual
    -0.56
    POSITIVE LOGITS
    o
    1.07
    xi
    1.03
    r
    1.00
    qi
    0.99
    XL
    0.99
    q
    0.98
    z
    0.98
    aq
    0.95
    E
    0.94
    a
    0.93
    Act Density 0.193%

    No Known Activations