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

    Neuronpedia

    INDEX
    Explanations

    locations or buildings with the word "Palace."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various palaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    schild
    -0.75
    ï¸ı
    -0.68
    err
    -0.68
    REE
    -0.68
    rss
    -0.67
    EMP
    -0.67
    rd
    -0.66
    CAST
    -0.66
    ACTED
    -0.65
    LER
    -0.65
    POSITIVE LOGITS
     Palace
    0.87
    ibur
    0.78
    monary
    0.77
    osaurs
    0.76
    gur
    0.74
     intrigue
    0.74
     Hotel
    0.74
     entrances
    0.72
     intrig
    0.72
     maiden
    0.71
    Act Density 0.017%

    No Known Activations