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

    Neuronpedia

    INDEX
    Explanations

    patterns of parentheses and brackets in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    opening delimiters followed by abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     polaire
    -0.52
     abstrait
    -0.50
     Paix
    -0.50
    Pozdrawiam
    -0.49
     Marín
    -0.49
     parís
    -0.48
     inoxidable
    -0.47
    bcryptjs
    -0.47
     Aragón
    -0.47
     Defensa
    -0.47
    POSITIVE LOGITS
    (.
    2.39
     (.
    1.79
     [.
    1.09
    [.
    1.05
     (*.
    1.01
    (+
    0.91
    (,
    0.91
    =.
    0.90
    (-
    0.87
     <.
    0.85
    Act Density 0.003%

    No Known Activations