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

    Neuronpedia

    INDEX
    Explanations

    numerical data, specifically percentages and statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical percentages indicating significant changes or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Machines
    -0.77
     devils
    -0.73
     machines
    -0.72
     Halls
    -0.72
     IDs
    -0.70
     memories
    -0.69
     wills
    -0.67
    ATURES
    -0.67
     establishments
    -0.67
     avenues
    -0.66
    POSITIVE LOGITS
    %-
    1.12
    %
    1.03
     percent
    1.02
    percent
    0.96
     percentage
    0.93
     percentile
    0.93
     fold
    0.89
     rating
    0.89
    fold
    0.88
     multiplier
    0.88
    Act Density 0.111%

    No Known Activations