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

    Neuronpedia

    INDEX
    Explanations

    terms related to various topics such as mutations, users, medals, school, submarines, players, trees, sellers, referees, test flights, exceptions, songs, wins, fossils, arguments, hostages, students, distributions, goals, monsters, registers, candidates

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scientific data, measurement, and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ecause
    -0.81
    peed
    -0.75
    ync
    -0.74
    actionDate
    -0.74
    ocobo
    -0.74
    aft
    -0.68
    ftime
    -0.68
    20439
    -0.68
    cale
    -0.66
     largeDownload
    -0.66
    POSITIVE LOGITS
    pool
    0.90
    ry
    0.87
     count
    0.87
    izations
    0.84
    yards
    0.84
    fleet
    0.82
    holders
    0.79
     pools
    0.78
    lets
    0.78
    sets
    0.78
    Act Density 0.837%

    No Known Activations