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

    Neuronpedia

    INDEX
    Explanations

    dates represented as the year 19 followed by another number

    oai_token-act-pair · gpt-3.5-turbo

    references to the year 1999

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orc
    -0.88
    aminer
    -0.84
    ensional
    -0.76
    plom
    -0.76
    ellation
    -0.73
    igent
    -0.72
    plings
    -0.71
    iants
    -0.70
    qqa
    -0.70
    oaded
    -0.69
    POSITIVE LOGITS
    th
    1.09
    âĸĪâĸĪ
    0.92
    09
    0.92
    07
    0.90
    08
    0.89
    61
    0.88
    05
    0.88
    03
    0.85
    06
    0.84
    04
    0.82
    Act Density 0.027%

    No Known Activations