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

    Neuronpedia

    INDEX
    Explanations

    keywords related to various specific topics, such as school, medals, palaces, towels, bubbles, paintings, branches, seats, combinations, elements, users, labels, centers, craters, farms, references, households, hacks, firehouses, invites

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to various entities or items in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    qua
    -0.82
    peed
    -0.79
    cale
    -0.77
    gow
    -0.76
    lip
    -0.76
    ĸļ
    -0.71
    arnaev
    -0.70
    ync
    -0.70
    pless
    -0.69
    aft
    -0.66
    POSITIVE LOGITS
     count
    0.88
    holders
    0.88
     counts
    0.87
    Types
    0.82
    Names
    0.80
     clusters
    0.77
    Count
    0.76
    001
    0.75
     assortment
    0.74
     holders
    0.72
    Act Density 0.677%

    No Known Activations