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

    Neuronpedia

    INDEX
    Explanations

    dates in different formats

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     predec
    -0.59
    dinand
    -0.57
    edIn
    -0.57
     undermin
    -0.55
    ogether
    -0.54
     recourse
    -0.54
    Empty
    -0.53
     nearest
    -0.53
     Vaugh
    -0.52
     rightful
    -0.51
    POSITIVE LOGITS
     RELEASE
    0.62
     OnePlus
    0.61
    DragonMagazine
    0.61
    ISON
    0.58
     Xiaomi
    0.58
     UKIP
    0.58
     ):
    0.57
    actionDate
    0.57
     Motorola
    0.57
     Samsung
    0.52
    Act Density 0.266%

    No Known Activations