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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and associated possessive language

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

    my possession of objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perdere
    -0.33
     kohta
    -0.32
     caused
    -0.30
    tahankan
    -0.29
    šanai
    -0.28
     atendido
    -0.28
     bēr
    -0.28
    ET
    -0.28
    owano
    -0.28
     is
    -0.27
    POSITIVE LOGITS
     protoimpl
    0.94
    Personendaten
    0.90
     ddelwed
    0.89
    <unused8>
    0.77
    <unused51>
    0.77
    <unused23>
    0.77
    <unused52>
    0.77
    InjectAttribute
    0.77
    [@BOS@]
    0.77
    <unused14>
    0.77
    Act Density 0.060%

    No Known Activations