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

    Neuronpedia

    INDEX
    Explanations

    timestamps or numbers in a certain format

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical data, particularly associated with votes or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istical
    -0.77
    arent
    -0.76
    istically
    -0.74
     Dull
    -0.74
    ggies
    -0.72
    ional
    -0.71
     splash
    -0.67
     Dare
    -0.66
    ioned
    -0.65
    ategic
    -0.65
    POSITIVE LOGITS
    09
    0.89
    089
    0.83
    088
    0.83
    793
    0.79
    08
    0.78
    052
    0.78
    090
    0.76
    06
    0.76
    ¢
    0.76
    059
    0.75
    Act Density 0.019%

    No Known Activations