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

    Neuronpedia

    INDEX
    Explanations

    names of historical or famous palaces

    oai_token-act-pair · gpt-3.5-turbo

    references to specific palaces and related locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    schild
    -0.77
    INESS
    -0.73
    CAST
    -0.73
    nir
    -0.73
    enegger
    -0.71
    acted
    -0.69
    mie
    -0.68
    err
    -0.68
    rss
    -0.68
    ï¸ı
    -0.68
    POSITIVE LOGITS
     Palace
    0.97
     Theatre
    0.78
     Hotel
    0.77
    gur
    0.75
     courtyard
    0.74
     intrigue
    0.74
     intrig
    0.74
     entrances
    0.72
    lain
    0.72
    osaurs
    0.71
    Act Density 0.026%

    No Known Activations