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

    Neuronpedia

    INDEX
    Explanations

    specific articles, prepositions, and conjunctions that indicate relationships between concepts or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aktu
    -0.15
    eya
    -0.14
    edly
    -0.14
    948
    -0.14
    _mE
    -0.14
    оÑĢони
    -0.14
    ÙIJÙĩ
    -0.14
    utan
    -0.13
    SPATH
    -0.13
     اع
    -0.13
    POSITIVE LOGITS
    ëŀĮ
    0.17
    antee
    0.15
    ting
    0.15
     bast
    0.15
    BuilderInterface
    0.15
     Oaks
    0.14
    ante
    0.14
     Gle
    0.14
    ugins
    0.13
    uer
    0.13
    Act Density 0.619%

    No Known Activations