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

    Neuronpedia

    INDEX
    Explanations

    words related to duties, tasks, and obligations

    oai_token-act-pair · gpt-3.5-turbo

    references to duties or obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ator
    -0.68
    inton
    -0.67
    aneously
    -0.64
    bay
    -0.63
    vae
    -0.62
    Rail
    -0.62
    alter
    -0.62
    eb
    -0.61
    imar
    -0.61
    ibur
    -0.61
    POSITIVE LOGITS
     obligations
    1.10
     responsibilities
    1.06
    afety
    0.92
    urden
    0.90
     owed
    0.82
     incurred
    0.81
     arrang
    0.77
     liabilities
    0.76
    ngth
    0.74
     citiz
    0.74
    Act Density 0.009%

    No Known Activations