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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific individual's name "Anderson" with varying degrees of activations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    BOOK
    -0.78
    soever
    -0.78
    ebook
    -0.72
    board
    -0.70
    misc
    -0.70
    kered
    -0.70
    oppers
    -0.69
    PER
    -0.69
    graded
    -0.67
    boards
    -0.67
    POSITIVE LOGITS
     Silva
    0.98
     Osw
    0.88
     Cooper
    0.85
     Robbins
    0.77
     Knox
    0.75
    quist
    0.74
     Anderson
    0.68
     Ashe
    0.68
     Hopkins
    0.67
     Watts
    0.67
    Act Density 0.110%

    No Known Activations