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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases involving quantities and qualities

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

    than followed by comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.76
     typelib
    -0.69
    Personensuche
    -0.63
    ReusableCell
    -0.61
    ftagPool
    -0.59
     disambiguazione
    -0.57
    ChromeDriver
    -0.55
     snippetHide
    -0.54
    Legături
    -0.54
    GEBURTSDATUM
    -0.54
    POSITIVE LOGITS
    bunal
    0.38
     zus
    0.32
    tim
    0.31
     Dicapai
    0.30
    endregion
    0.30
    istle
    0.30
    rawan
    0.30
     zug
    0.30
    findpost
    0.30
     there
    0.30
    Act Density 1.935%

    No Known Activations