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

    Neuronpedia

    INDEX
    Explanations

    references to the 21st century

    oai_token-act-pair · gpt-3.5-turbo

    references to the 21st century

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     externalToEVAOnly
    -0.84
    backs
    -0.68
    atics
    -0.66
    opsis
    -0.64
     plain
    -0.64
    ched
    -0.62
     ultras
    -0.59
    back
    -0.59
     Plain
    -0.59
     gren
    -0.57
    POSITIVE LOGITS
    st
    1.87
    ST
    1.09
    WI
    0.88
    sta
    0.85
    506
    0.78
    50
    0.78
    nd
    0.77
    507
    0.77
    sts
    0.75
    503
    0.75
    Act Density 0.092%

    No Known Activations