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

    Neuronpedia

    INDEX
    Explanations

    last names, statistics, and sports-related terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    soType
    -0.89
    isSpecialOrderable
    -0.82
    insula
    -0.81
    channelAvailability
    -0.79
     goodbye
    -0.68
     Saud
    -0.67
     Intro
    -0.66
    Word
    -0.66
    actionDate
    -0.66
     Fein
    -0.65
    POSITIVE LOGITS
     averaged
    1.46
     totaled
    1.31
     averages
    1.25
     racked
    1.23
     tallied
    1.22
     averaging
    1.18
     scored
    1.15
     amassed
    1.08
     logged
    1.08
     recorded
    1.05
    Act Density 0.140%

    No Known Activations