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

    Neuronpedia

    INDEX
    Explanations

    connections and interactions within groups or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cab
    -0.17
     Watt
    -0.16
     Mush
    -0.15
    ewis
    -0.15
     Har
    -0.14
    ilip
    -0.14
    .har
    -0.14
     Sea
    -0.14
     Trav
    -0.14
     &
    -0.14
    POSITIVE LOGITS
    llib
    0.18
    -toggler
    0.15
     заÑģÑĤÑĥп
    0.14
     çķ
    0.14
    TestCategory
    0.14
    avin
    0.14
    imoto
    0.14
    ê³¼ìĿĺ
    0.14
    лик
    0.14
    мÑĸнÑĸ
    0.14
    Act Density 0.995%

    No Known Activations