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

    Neuronpedia

    INDEX
    Explanations

    lyrics within the text

    oai_token-act-pair · gpt-3.5-turbo

    references to song lyrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aples
    -0.80
    erate
    -0.75
     Leap
    -0.72
     Dull
    -0.67
    alin
    -0.67
    OTAL
    -0.65
    DERR
    -0.64
     Libre
    -0.64
    ITNESS
    -0.64
     Hutch
    -0.64
    POSITIVE LOGITS
     lyrics
    1.41
    mith
    1.22
    writer
    1.21
     lyric
    1.21
    writers
    1.18
     sung
    1.01
    yrics
    0.98
    writing
    0.98
    stress
    0.89
     vocals
    0.86
    Act Density 0.024%

    No Known Activations