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

    Neuronpedia

    INDEX
    Explanations

    references to bilingualism and languages in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Huffman
    -0.15
    uala
    -0.14
     Morr
    -0.14
    uthor
    -0.14
    erry
    -0.14
    ÑĢе
    -0.14
    ÑĢеÑĤ
    -0.13
    ensa
    -0.13
    ä»ĺ
    -0.13
    aldo
    -0.13
    POSITIVE LOGITS
     corner
    0.18
    yen
    0.17
    igue
    0.15
    ness
    0.15
    YGON
    0.15
    fos
    0.14
    -Clause
    0.14
     corners
    0.14
    iseum
    0.14
     Arc
    0.14
    Act Density 0.028%

    No Known Activations