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

    Neuronpedia

    INDEX
    Explanations

    patterns or sequences of numbers

    oai_token-act-pair · gpt-3.5-turbo

    strings of alphanumeric characters or formatted data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SUM
    -0.61
    20439
    -0.60
     SHARES
    -0.59
    ENCY
    -0.59
     Explos
    -0.58
    820
    -0.58
    lihood
    -0.57
    76561
    -0.57
    gest
    -0.57
    TAIN
    -0.56
    POSITIVE LOGITS
    ubi
    0.72
     payday
    0.69
     commuting
    0.66
     acad
    0.65
    aido
    0.65
    awaru
    0.65
    ignty
    0.62
    assadors
    0.62
    aving
    0.61
    anooga
    0.60
    Act Density 0.045%

    No Known Activations