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

    Neuronpedia

    INDEX
    Explanations

    words related to projects, such as events, games, movements, projects, films, books, movies, products, shows, songs, albums, tours, recordings, features, genres, speeches, and studies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of media and creative projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Qiao
    -0.61
    inez
    -0.60
    NetMessage
    -0.60
     Earthqu
    -0.58
     Levels
    -0.56
     Electricity
    -0.56
     Roads
    -0.55
    suff
    -0.55
    Contents
    -0.55
    Images
    -0.55
    POSITIVE LOGITS
     thats
    0.90
     like
    0.81
     guy
    0.80
     worthy
    0.79
    writer
    0.78
     gimmick
    0.75
     standpoint
    0.74
     theorist
    0.73
    iologist
    0.71
     THAT
    0.70
    Act Density 0.436%

    No Known Activations