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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a listing or enumeration of items

    oai_token-act-pair · gpt-3.5-turbo

    the word "an"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    'an' or ' an' token

    Explanation Uploaded by User
    New Auto-Interp
    Negative Logits
     Jagu
    -0.71
     Borders
    -0.68
     Bris
    -0.65
     Shake
    -0.64
     branches
    -0.64
     Howe
    -0.63
    stones
    -0.62
     Greene
    -0.61
     possessions
    -0.61
     McKay
    -0.61
    POSITIVE LOGITS
    abolic
    0.96
    alysed
    0.93
    notation
    0.92
    onymous
    0.91
    cients
    0.88
    notations
    0.85
    onym
    0.83
    olin
    0.81
    alyses
    0.80
    ointed
    0.80
    Act Density 0.022%

    No Known Activations