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

    Neuronpedia

    INDEX
    Explanations

    references to literary awards and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.71
     kasarigan
    -0.69
     débat
    -0.68
    savevideo
    -0.67
     invokingState
    -0.66
     Video
    -0.66
    VideoView
    -0.62
    Video
    -0.62
    Revenir
    -0.59
    Aholisi
    -0.59
    POSITIVE LOGITS
     novels
    0.89
     fiction
    0.89
     readers
    0.77
     novel
    0.75
     authors
    0.74
     author
    0.73
     books
    0.71
     writing
    0.71
     Goodreads
    0.71
     writers
    0.71
    Act Density 0.376%

    No Known Activations