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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'been'

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "there have been" which indicates occurrences or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arta
    -0.88
    arily
    -0.68
    would
    -0.67
     Taxes
    -0.66
    ribe
    -0.65
    poses
    -0.64
    Imagine
    -0.62
    ooter
    -0.62
     Imagine
    -0.61
    ooters
    -0.59
    POSITIVE LOGITS
     plenty
    0.91
    cffffcc
    0.82
     murm
    0.79
     unanimous
    0.77
     enough
    0.75
     tremendous
    0.69
     concerted
    0.69
     ample
    0.68
     speculation
    0.66
    ļé
    0.65
    Act Density 0.022%

    No Known Activations