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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to visual observations

    oai_token-act-pair · gpt-3.5-turbo

    instances of repetitive structures or patterns in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ominated
    -0.65
    ãĥĥãĥī
    -0.62
    ĨĴ
    -0.60
    Need
    -0.59
     Chapters
    -0.56
    Regular
    -0.56
    ologies
    -0.55
    Category
    -0.55
    Daddy
    -0.54
    Come
    -0.53
    POSITIVE LOGITS
     Photograph
    0.98
    window
    0.95
     photographed
    0.92
     photograph
    0.90
     photo
    0.89
     Shutterstock
    0.89
     PHOTO
    0.86
     REUTERS
    0.85
     Flickr
    0.85
     Photo
    0.84
    Act Density 0.517%

    No Known Activations