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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and possessive terms

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

    Possessive pronouns followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns and what they own

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    쿵
    -0.40
    volution
    -0.39
     the
    -0.38
    ERING
    -0.38
    Filler
    -0.37
    ervices
    -0.37
    HasForeignKey
    -0.36
     cjs
    -0.36
     собой
    -0.36
     resourceCulture
    -0.36
    POSITIVE LOGITS
    OGND
    0.73
    цездатний
    0.68
     мәкал
    0.58
     архивлан
    0.57
     enfans
    0.57
    RegistryLite
    0.56
    pantalón
    0.52
    hyrchwyd
    0.50
     estekak
    0.50
     ویکی‌پدی
    0.50
    Act Density 0.585%

    No Known Activations