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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "as" in various contexts, particularly when used to make comparisons or introduce clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disponibilités
    -0.80
     ogóle
    -0.69
    躇
    -0.66
    leria
    -0.65
     ramah
    -0.64
     bacio
    -0.63
     caminhada
    -0.62
    efte
    -0.62
    jfree
    -0.62
    ッポン
    -0.61
    POSITIVE LOGITS
     As
    1.19
    As
    1.17
     متعلقه
    0.95
     تضيفلها
    0.85
    as
    0.73
     ahogy
    0.67
     Paglinawan
    0.63
    Towards
    0.62
     as
    0.61
     arsenic
    0.61
    Act Density 0.107%

    No Known Activations