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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مض
    -0.69
     مشار
    -0.69
     prodi
    -0.67
    cyjny
    -0.67
    τουργ
    -0.66
    DockStyle
    -0.65
     opis
    -0.64
    etheless
    -0.64
     arran
    -0.64
    enegal
    -0.63
    POSITIVE LOGITS
     {.
    0.87
    */].
    0.75
    (".")
    0.74
     }}$.
    0.74
    ('.')
    0.74
    .$.
    0.72
    __).
    0.70
    ("%.
    0.70
    \.
    0.69
    ("$.
    0.69
    Act Density 0.393%

    No Known Activations