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

    Neuronpedia

    INDEX
    Explanations

    phrases related to presenting conclusions or results

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to groundbreaking achievements or historical firsts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.79
    interstitial
    -0.71
     Cancel
    -0.70
     Cance
    -0.69
     Courage
    -0.69
     Reneg
    -0.67
     Parkway
    -0.62
     EntityItem
    -0.61
     inconven
    -0.61
    itton
    -0.61
    POSITIVE LOGITS
     conclusive
    1.46
     definitive
    1.37
     definitively
    1.23
     scientifically
    1.22
     empir
    1.21
     adequately
    1.14
     systematically
    1.12
     rigorous
    1.12
     precise
    1.09
     reliably
    1.07
    Act Density 0.197%

    No Known Activations