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

    Neuronpedia

    INDEX
    Explanations

    instances of negation or expressions of uncertainty

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

    Apostrophes at the beginning of a sentence

    np_acts-logits-general · gemini-2.0-flash

    apostrophes in contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.70
     الحره
    -0.68
    tagHelperRunner
    -0.66
    Хьажоргаш
    -0.63
    addGap
    -0.62
     المعيارى
    -0.61
     AssemblyCulture
    -0.57
    AnchorStyles
    -0.56
     Мексичка
    -0.54
    ThroughAttribute
    -0.54
    POSITIVE LOGITS
    ’
    0.59
     the
    0.52
    magn
    0.46
    esthe
    0.45
    周泽
    0.45
     Fav
    0.44
     Iter
    0.44
     The
    0.42
    The
    0.42
    ESCO
    0.41
    Act Density 0.013%

    No Known Activations