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

    Neuronpedia

    INDEX
    Explanations

    words related to obligations or duties

    oai_token-act-pair · gpt-3.5-turbo

    terms related to obligations and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atin
    -0.82
    vill
    -0.81
    vae
    -0.81
    oco
    -0.81
    auder
    -0.74
    upt
    -0.74
    corn
    -0.69
    nick
    -0.69
    stocks
    -0.69
    iverpool
    -0.69
    POSITIVE LOGITS
     obligation
    1.12
     obligations
    1.09
     owed
    1.04
     obliged
    1.03
     obligated
    0.92
     uphold
    0.83
     forgiveness
    0.80
     oblig
    0.78
     incurred
    0.76
     compel
    0.75
    Act Density 0.030%

    No Known Activations