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

    Neuronpedia

    INDEX
    Explanations

    legal terminology and phrases related to formal statements or classifications

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

    rephrasing and paraphrasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.61
    LookAnd
    -0.58
    قایناقلار
    -0.53
     NSCoder
    -0.52
    InteropServices
    -0.50
     AssemblyCulture
    -0.50
    Skocz
    -0.47
    >>;
    -0.46
     />\
    -0.46
     estekak
    -0.46
    POSITIVE LOGITS
     paraphrase
    1.51
     paraph
    1.45
    aph
    0.84
    rasing
    0.75
    rased
    0.71
    frase
    0.64
     parap
    0.56
    phrase
    0.52
    фра
    0.48
     phrasing
    0.46
    Act Density 0.008%

    No Known Activations