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

    Neuronpedia

    INDEX
    Explanations

    references to lyrics in text

    oai_token-act-pair · gpt-3.5-turbo

    references to song lyrics and their qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erate
    -0.75
    aples
    -0.75
    alin
    -0.73
     Leap
    -0.65
    OTAL
    -0.65
     Dull
    -0.63
    negie
    -0.62
     Vive
    -0.62
    owship
    -0.61
     Buk
    -0.60
    POSITIVE LOGITS
     lyrics
    1.47
     lyric
    1.24
    writer
    1.19
    mith
    1.18
    writers
    1.17
    yrics
    1.02
     sung
    1.01
    writing
    1.00
     songs
    0.90
     melodies
    0.89
    Act Density 0.022%

    No Known Activations