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

    Neuronpedia

    INDEX
    Explanations

    phrases related to captions for images or articles, specifically indicating the end or beginning of captions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    bats
    -0.61
    ionage
    -0.60
     Beir
    -0.59
     fortun
    -0.57
     Faw
    -0.56
     accur
    -0.56
     Alv
    -0.56
    liest
    -0.56
     fuzz
    -0.56
    theless
    -0.55
    POSITIVE LOGITS
    ËĪ
    0.97
    Courtesy
    0.73
    wcsstore
    0.70
    Photos
    0.70
    img
    0.68
    entity
    0.67
    Film
    0.67
     Images
    0.66
     Shutterstock
    0.66
    gallery
    0.66
    Act Density 0.013%

    No Known Activations