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

    Neuronpedia

    INDEX
    Explanations

    Twitter activity related to scrolling or searching

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Production
    -0.66
    ajor
    -0.66
    kiss
    -0.64
    ependence
    -0.63
    Construction
    -0.63
    roit
    -0.63
    amen
    -0.62
    idis
    -0.62
    breaking
    -0.61
    interstitial
    -0.61
    POSITIVE LOGITS
     databases
    1.13
     archives
    1.04
     menus
    1.02
     google
    0.90
     pages
    0.90
     folders
    0.89
     browsing
    0.88
     browse
    0.88
     listings
    0.87
     archived
    0.87
    Act Density 0.164%

    No Known Activations