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

    Neuronpedia

    INDEX
    Explanations

    references to ancient civilizations and their historical significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -toast
    -0.15
    èĮĤ
    -0.15
     Cater
    -0.15
     roman
    -0.14
     Muslim
    -0.14
     Benedict
    -0.14
    roman
    -0.14
    Icons
    -0.14
     Muslims
    -0.14
    Muslim
    -0.14
    POSITIVE LOGITS
     tablet
    0.31
     Tablet
    0.31
     tablets
    0.30
     Tablets
    0.30
    tablet
    0.29
     Mes
    0.27
     Babylon
    0.25
     Hamm
    0.25
     Lars
    0.24
     Neo
    0.23
    Act Density 0.027%

    No Known Activations