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

    Neuronpedia

    INDEX
    Explanations

    instances of past occurrences or patterns

    oai_token-act-pair · gpt-3.5-turbo

    references to past events or repeated occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UME
    -0.77
    Accessory
    -0.75
    urden
    -0.75
     Components
    -0.73
    dit
    -0.72
     2019
    -0.67
    ogle
    -0.66
     Tycoon
    -0.65
    anium
    -0.65
    andise
    -0.64
    POSITIVE LOGITS
     unsuccessfully
    0.94
     lately
    0.82
     presidents
    0.81
     administrations
    0.79
     mayors
    0.77
     Presidents
    0.77
     civilizations
    0.76
     incarn
    0.76
     occasions
    0.75
     anecd
    0.75
    Act Density 0.583%

    No Known Activations