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

    Neuronpedia

    INDEX
    Explanations

    numerical data and values

    oai_token-act-pair · gpt-3.5-turbo

    references to real-life applications and instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rica
    -0.77
     AVG
    -0.74
     Norris
    -0.69
    ynski
    -0.68
     Cooke
    -0.68
     ..........
    -0.65
     Coch
    -0.62
     Carbuncle
    -0.62
     SHARES
    -0.62
     Moreno
    -0.61
    POSITIVE LOGITS
    estate
    1.34
    life
    1.04
    sounding
    1.03
    terms
    0.99
    world
    0.98
    time
    0.97
    money
    0.95
    science
    0.95
    angled
    0.92
    sized
    0.92
    Act Density 0.028%

    No Known Activations