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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and the concepts of null and loss associated with dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IC
    -0.15
    ircle
    -0.14
    hec
    -0.14
    oxic
    -0.14
    ount
    -0.14
    805
    -0.14
    yst
    -0.14
    art
    -0.14
    ega
    -0.14
    fram
    -0.14
    POSITIVE LOGITS
    rack
    0.15
     maduras
    0.15
    ĵĺ
    0.15
    cum
    0.14
    ãĤĨ
    0.14
    絶
    0.14
    _fixture
    0.14
    ãĥķãĤ
    0.14
    ساÙĨÛĮ
    0.14
    ForResource
    0.13
    Act Density 0.002%

    No Known Activations