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

    Neuronpedia

    INDEX
    Explanations

    dates in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    date references in a specific format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     accus
    -0.72
    izon
    -0.68
    eston
    -0.67
    onym
    -0.65
     antiv
    -0.64
     Pow
    -0.61
    lain
    -0.61
    CLUD
    -0.61
    otine
    -0.59
     wand
    -0.58
    POSITIVE LOGITS
    å¹
    0.88
    02
    0.85
    01
    0.83
    January
    0.81
    2016
    0.81
    04
    0.80
    2011
    0.80
    released
    0.79
    release
    0.78
    February
    0.78
    Act Density 0.095%

    No Known Activations