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

    Neuronpedia

    INDEX
    Explanations

    the auxiliary verb "had" in various forms and constructions

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

    had past participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.43
     дописавши
    -0.41
    principalTable
    -0.40
    IntoConstraints
    -0.40
    afficheront
    -0.39
     архивлан
    -0.39
    setVerticalGroup
    -0.35
     noDo
    -0.34
     صوتيه
    -0.33
     känns
    -0.33
    POSITIVE LOGITS
     Administrativna
    0.69
    iſche
    0.59
    ulele
    0.59
    iſchen
    0.58
    ︎
    0.57
     erſten
    0.57
     geweſen
    0.57
    ypeł
    0.57
     verſch
    0.57
     ſeyn
    0.56
    Act Density 0.023%

    No Known Activations