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

    Neuronpedia

    INDEX
    Explanations

    references to geographic locations, specifically islands and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lero
    -0.18
    orgia
    -0.16
    orest
    -0.15
    azon
    -0.15
    intree
    -0.15
     mantle
    -0.14
    esson
    -0.14
    бÑĥÑĤ
    -0.14
    ège
    -0.14
    azing
    -0.14
    POSITIVE LOGITS
     island
    0.20
     Island
    0.19
     islands
    0.17
    intern
    0.16
    inky
    0.15
    ÑģÑĤÑĢов
    0.15
     loft
    0.15
    ÑģÑĮого
    0.14
    ä¸ĬçļĦ
    0.14
     Islands
    0.14
    Act Density 0.096%

    No Known Activations