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

    Neuronpedia

    INDEX
    Explanations

    dates written in the format "19XX"

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 19, particularly in a historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aminer
    -0.90
    orc
    -0.89
    ensional
    -0.79
    anguage
    -0.78
    arling
    -0.74
    endum
    -0.72
    oaded
    -0.71
    ional
    -0.71
    igent
    -0.70
    othy
    -0.70
    POSITIVE LOGITS
    th
    1.01
    âĸĪâĸĪ
    0.94
    61
    0.81
    05
    0.80
    07
    0.79
    08
    0.79
    09
    0.78
    06
    0.77
    059
    0.76
    03
    0.74
    Act Density 0.025%

    No Known Activations