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

    Neuronpedia

    INDEX
    Explanations

    commas and quotation marks in text, indicating dialogue or quoted speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iral
    -0.14
    ictor
    -0.14
    ienne
    -0.13
     lại
    -0.13
    rol
    -0.13
    uther
    -0.13
    (.)
    -0.13
    ans
    -0.13
    hl
    -0.13
    ural
    -0.12
    POSITIVE LOGITS
     said
    0.26
     says
    0.22
     wrote
    0.19
     he
    0.17
    said
    0.15
     writes
    0.15
     sai
    0.15
     reads
    0.14
     Purple
    0.14
     paraph
    0.14
    Act Density 0.091%

    No Known Activations