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

    Neuronpedia

    INDEX
    Explanations

    negative comparisons or critiques regarding technological advancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dickinson
    -0.70
     Rica
    -0.70
     Cato
    -0.69
     Cambodia
    -0.65
     Hoo
    -0.65
     philosoph
    -0.65
     Cassidy
    -0.64
     Rouge
    -0.63
     embarrassment
    -0.63
    ople
    -0.62
    POSITIVE LOGITS
    hour
    1.31
    year
    1.26
    degree
    1.21
    years
    1.21
    digit
    1.21
    inch
    1.20
    month
    1.18
    minute
    1.17
    sided
    1.16
    Zip
    1.15
    Act Density 0.088%

    No Known Activations