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

    Neuronpedia

    INDEX
    Explanations

    references to different grammatical persons in language and their specific usages

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

    first and third person

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tså
    -0.42
    ⟬
    -0.38
    –¿
    -0.38
    JsonFormat
    -0.38
    InputBorder
    -0.37
    TestingModule
    -0.35
    Ведь
    -0.35
     pacchetto
    -0.34
    出版年
    -0.34
    Disaster
    -0.34
    POSITIVE LOGITS
     person
    0.74
    Person
    0.73
    person
    0.73
     PERSON
    0.71
     Person
    0.70
    PERSON
    0.61
    #+#
    0.60
     شخص
    0.60
    Personen
    0.54
    :+:
    0.53
    Act Density 0.008%

    No Known Activations