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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns indicating ownership or association

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

    own / self / possessive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hyrchwyd
    -0.46
     arru
    -0.34
     pData
    -0.32
    /$',
    -0.31
    readValue
    -0.30
    ősz
    -0.29
    Panamoan
    -0.29
     лю
    -0.29
     находи
    -0.28
    DotNet
    -0.28
    POSITIVE LOGITS
     sarili
    0.78
     own
    0.67
    selves
    0.62
     eigenen
    0.60
     próprios
    0.55
     eigenes
    0.53
     sendiri
    0.52
     eigene
    0.52
     propias
    0.52
     svoje
    0.52
    Act Density 0.117%

    No Known Activations