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

    Neuronpedia

    INDEX
    Explanations

    lyrics in songs, especially focused on particular words or themes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    aples
    -0.74
     Leap
    -0.70
     Norton
    -0.69
    ITNESS
    -0.69
    erate
    -0.68
    OTAL
    -0.68
    Ĭ±
    -0.66
    BLIC
    -0.65
     Centauri
    -0.65
    Bir
    -0.63
    POSITIVE LOGITS
     lyrics
    1.37
    mith
    1.29
    writer
    1.23
     lyric
    1.21
    writers
    1.19
     sung
    1.18
    writing
    1.03
    yrics
    1.02
     melodies
    0.97
     melody
    0.95
    Act Density 0.035%

    No Known Activations