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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "be" and its various forms in context

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

    be able to

    np_acts-logits-general · gemini-2.5-flash-lite

    It detects verbs that mark a clause's predicate—especially auxiliaries and state/ability verbs (e.g., "be", "able", "can", contractions like "'re", and similar forms).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    breng
    -0.47
     Biôgrafia
    -0.46
     ویکی‌پدی
    -0.45
     gelukkig
    -0.40
    tangentMode
    -0.39
     mascotas
    -0.39
    ISTICS
    -0.38
     chrétien
    -0.36
     avanzado
    -0.36
    OGND
    -0.36
    POSITIVE LOGITS
    jooq
    0.60
    mybatisplus
    0.51
     esternos
    0.51
    Życiorys
    0.49
    invokeLater
    0.49
    Наводи
    0.48
     nakalista
    0.48
    Atsauces
    0.47
    הערות
    0.47
    Lähteet
    0.47
    Act Density 0.686%

    No Known Activations