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

    Neuronpedia

    INDEX
    Explanations

    references to ownership and possession

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

    "their" preceding a noun

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mwenye
    -0.67
     själv
    -0.64
     wife
    -0.61
    simpleType
    -0.60
     magát
    -0.60
     kendisi
    -0.60
     istrinya
    -0.59
    asantry
    -0.59
    felf
    -0.59
     himself
    -0.58
    POSITIVE LOGITS
     their
    1.77
    Their
    1.77
    their
    1.68
     Their
    1.62
     lives
    1.45
     themselves
    1.41
     THEIR
    1.35
     leurs
    1.32
    themselves
    1.32
    各自
    1.30
    Act Density 0.426%

    No Known Activations