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

    Neuronpedia

    INDEX
    Explanations

    instances of apostrophes in written text

    oai_token-act-pair · gemini-2.0-flash

    specific characters or symbols used in various contexts

    np_token-act-pair-logits · gpt-4o-mini

    apostrophe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (
    -0.53
    ell
    -0.50
    pses
    -0.50
    illon
    -0.46
     regist
    -0.44
    广西
    -0.44
     el
    -0.43
     Register
    -0.42
    метров
    -0.42
     est
    -0.42
    POSITIVE LOGITS
     transfieras
    0.78
    ViewFeatures
    0.70
     ostavi
    0.60
     Мексичка
    0.56
    memoized
    0.56
     leopardo
    0.55
    verwijspagina
    0.55
     intStringLen
    0.55
     fidé
    0.54
    ftagPool
    0.54
    Act Density 0.233%

    No Known Activations