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

    Neuronpedia

    INDEX
    Explanations

    words related to composition or composers

    oai_token-act-pair · gpt-3.5-turbo

    the stem "compos" regardless of its suffix or compound formation

    oai_token-act-pair · gpt-4-turbo

    references to composers in the context of music

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Breed
    -0.79
    GA
    -0.69
     Murdoch
    -0.69
     Hatch
    -0.68
     Europeans
    -0.68
     Zucker
    -0.67
    Gamer
    -0.65
     Forbes
    -0.65
     Inqu
    -0.63
     Gors
    -0.62
    POSITIVE LOGITS
     compos
    1.21
    itional
    1.08
     arrang
    0.88
    itions
    0.88
     nomine
    0.87
    itionally
    0.86
    itivity
    0.85
    stress
    0.84
    iosyn
    0.83
     subsequ
    0.83
    Act Density 0.010%

    No Known Activations