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

    Neuronpedia

    INDEX
    Explanations

    references to Poland or things related to Polish culture

    oai_token-act-pair · gpt-3.5-turbo

    references to Polish people, culture, or entities associated with Poland

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.77
     Fernand
    -0.76
     Tsukuyomi
    -0.75
     Hawkins
    -0.75
     Gund
    -0.74
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.70
    houn
    -0.69
    76561
    -0.68
    essions
    -0.68
     sinful
    -0.67
    POSITIVE LOGITS
     Polish
    3.40
     polish
    2.66
     Poles
    2.28
    Pol
    2.20
     Poland
    1.77
    pol
    1.54
     Czech
    1.43
     Lithuan
    1.42
     Slov
    1.39
     Warsaw
    1.36
    Act Density 0.016%

    No Known Activations