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

    Neuronpedia

    INDEX
    Explanations

    references to individuality and personal ownership

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

    personal creation and ownership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.60
     GenerationType
    -0.47
    enterOuterAlt
    -0.45
     estekak
    -0.44
    ValueStyle
    -0.42
    FunctionFlags
    -0.42
    ьаж
    -0.40
    Viitteet
    -0.40
    BeginContext
    -0.38
    Tembelea
    -0.38
    POSITIVE LOGITS
     own
    0.57
    own
    0.51
     włas
    0.49
    เอง
    0.48
     sendiri
    0.48
     Own
    0.47
    Own
    0.47
     eigene
    0.45
     eigener
    0.44
     соб
    0.42
    Act Density 0.053%

    No Known Activations