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

    Neuronpedia

    INDEX
    Explanations

    mentions of regulations or specific legal terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Under" followed by numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aukee
    -0.80
     distur
    -0.67
    76561
    -0.66
    ospace
    -0.61
     gulf
    -0.60
     mov
    -0.60
     gor
    -0.59
    ibia
    -0.57
     audiences
    -0.57
    assic
    -0.56
    POSITIVE LOGITS
    neath
    1.35
    lying
    1.14
    graduate
    1.10
    stood
    0.98
    mining
    0.98
    cover
    0.95
    stant
    0.95
    statement
    0.94
    whelming
    0.93
    taking
    0.93
    Act Density 0.024%

    No Known Activations