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

    Neuronpedia

    INDEX
    Explanations

    various types of punctuation and function calls in code snippets

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

    punctuation and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     againſt
    -0.55
     juſ
    -0.51
     Gór
    -0.45
     ſur
    -0.44
     zéro
    -0.44
     perſon
    -0.44
     itſelf
    -0.43
     ſay
    -0.43
     paſſ
    -0.42
     ſever
    -0.42
    POSITIVE LOGITS
    <bos>
    0.79
    OGND
    0.72
    ("$.
    0.71
    ']").
    0.71
    دانشنامهٔ
    0.70
    ]').
    0.66
    }`).
    0.65
    Tembelea
    0.65
    */].
    0.64
    ())).
    0.64
    Act Density 0.034%

    No Known Activations