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

    Neuronpedia

    INDEX
    Explanations

    keywords related to orders or sequences

    oai_token-act-pair · gpt-3.5-turbo

    references to prior content or historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lua
    -0.78
    aliation
    -0.71
    alion
    -0.71
    rage
    -0.70
    abad
    -0.69
     ILCS
    -0.67
    kamp
    -0.66
    aleigh
    -0.65
    romeda
    -0.64
    ocracy
    -0.64
    POSITIVE LOGITS
     generations
    1.20
     incarn
    1.03
    ebin
    0.98
     incarnation
    0.97
     iterations
    0.92
     installments
    0.92
     editions
    0.88
    itiz
    0.85
     administrations
    0.84
    ĻĤ
    0.82
    Act Density 0.033%

    No Known Activations