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

    Neuronpedia

    INDEX
    Explanations

    instances of the article "a" and variations of "an."

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

    a technical or specific noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acaso
    -0.46
     extranjero
    -0.45
     peuple
    -0.43
     Italij
    -0.39
     Auffassung
    -0.38
     chrétien
    -0.35
    #
    -0.35
     république
    -0.35
     enfermo
    -0.35
     asesinado
    -0.34
    POSITIVE LOGITS
    GEBURTSDATUM
    0.96
     zwiſchen
    0.81
    IBOutlet
    0.80
    ſſung
    0.77
     ddelwed
    0.76
    ſicht
    0.76
    ConstraintMaker
    0.75
    iſche
    0.73
    iſchen
    0.72
    [@BOS@]
    0.72
    Act Density 0.031%

    No Known Activations