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

    Neuronpedia

    INDEX
    Explanations

    a determiner 'a' followed by a noun

    oai_token-act-pair · gpt-3.5-turbo

    the article "a" or "an" and its frequency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    words
    -0.70
     aloud
    -0.69
    tests
    -0.68
    Edit
    -0.67
     Blacks
    -0.67
     Acts
    -0.65
    Rules
    -0.65
    tm
    -0.64
    Events
    -0.63
    letters
    -0.62
    POSITIVE LOGITS
     lot
    1.26
     plethora
    1.19
     tremendous
    1.07
     considerable
    1.06
     bunch
    1.03
     substantial
    1.03
     glimpse
    1.02
     sizeable
    1.00
     huge
    1.00
     sizable
    0.97
    Act Density 0.265%

    No Known Activations