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

    Neuronpedia

    INDEX
    Explanations

    the phrase "View all" followed by capitalized words

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    #$
    -0.67
    Ħ¢
    -0.64
    bery
    -0.62
    cest
    -0.62
    kh
    -0.61
    othing
    -0.61
    Sov
    -0.61
    pac
    -0.60
    ursday
    -0.59
    ufact
    -0.59
    POSITIVE LOGITS
     âĸ
    0.65
     ARTICLE
    0.65
     gallery
    0.64
     Loading
    0.64
    Privacy
    0.61
    umbnail
    0.61
    arger
    0.61
    âĶĢâĶĢâĶĢâĶĢ
    0.61
    interstitial
    0.61
     »
    0.60
    Act Density 0.037%

    No Known Activations