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

    Neuronpedia

    INDEX
    Explanations

    references to possessive pronouns, particularly 'its'

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

    "its" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    possessive its before nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tulane
    -0.55
    <bos>
    -0.52
    py
    -0.50
     Athenians
    -0.49
    table
    -0.47
     Ananda
    -0.44
     probleme
    -0.44
     Dede
    -0.43
    test
    -0.42
    HY
    -0.42
    POSITIVE LOGITS
     its
    1.18
     Its
    1.15
    Its
    1.09
     ITS
    1.09
    它的
    1.00
    its
    0.86
     المعيارى
    0.86
     Itself
    0.85
    saraba
    0.83
    Twas
    0.82
    Act Density 0.202%

    No Known Activations