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

    Neuronpedia

    INDEX
    Explanations

    titles of books and articles

    oai_token-act-pair · gpt-3.5-turbo

    titles of books and their authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undai
    -0.82
    etooth
    -0.76
    xon
    -0.72
    agra
    -0.71
     trouble
    -0.70
     misunder
    -0.70
    udeb
    -0.69
    ison
    -0.68
    rost
    -0.68
    inarily
    -0.66
    POSITIVE LOGITS
     Definitive
    1.04
     Reloaded
    1.02
     Volume
    0.93
     Chains
    0.91
     Moving
    0.88
     Rebirth
    0.86
     Lessons
    0.86
     How
    0.84
     Principles
    0.83
     Reborn
    0.82
    Act Density 0.072%

    No Known Activations