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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by nouns

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of "of" followed by relevant subjects or descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Enlarge
    -0.73
    externalActionCode
    -0.63
    BuyableInstoreAndOnline
    -0.59
    tackle
    -0.58
    achable
    -0.58
    olini
    -0.57
    IONS
    -0.56
    few
    -0.56
     altogether
    -0.56
    eca
    -0.54
    POSITIVE LOGITS
     course
    0.74
    pires
    0.66
     these
    0.64
     consists
    0.64
     this
    0.63
     Bene
    0.62
     depends
    0.62
     Nanto
    0.61
     comprises
    0.59
     FANTASY
    0.58
    Act Density 0.242%

    No Known Activations