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

    Neuronpedia

    INDEX
    Explanations

    mentions of musical "tunes" or their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    tune and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.54
     Eriksson
    -0.50
     erwartet
    -0.49
     citoy
    -0.48
     Salazar
    -0.47
     Desai
    -0.46
     Salgado
    -0.45
     Salford
    -0.44
    BSD
    -0.44
     largest
    -0.44
    POSITIVE LOGITS
     tune
    2.20
     Tune
    2.06
    Tune
    1.92
    tune
    1.91
     tunes
    1.84
     Tunes
    1.57
     tuned
    1.48
    Tunes
    1.33
     tuning
    1.29
    tuned
    1.27
    Act Density 0.003%

    No Known Activations