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

    Neuronpedia

    INDEX
    Explanations

    mentions of personal accomplishments and experiences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    uden
    -0.76
    events
    -0.76
    encies
    -0.75
    mares
    -0.75
    onies
    -0.72
    answer
    -0.72
    iments
    -0.71
    ayers
    -0.70
    Edit
    -0.69
    Events
    -0.68
    POSITIVE LOGITS
     member
    1.15
     believer
    1.04
     supporter
    1.01
     participant
    1.01
     fixture
    0.99
     prisoner
    0.99
     follower
    0.97
     teenager
    0.94
     beneficiary
    0.93
     salesman
    0.93
    Act Density 0.257%

    No Known Activations