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

    Neuronpedia

    INDEX
    Explanations

    possessive constructions and contractions related to ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ’s
    -0.19
    å°ı说
    -0.19
    人åĵ¡
    -0.19
    ’re
    -0.18
    ’t
    -0.18
    å£°éŁ³
    -0.17
    ä¸ĢäºĽ
    -0.16
    ’n
    -0.16
    人æ°Ĺ
    -0.16
    äºĭ
    -0.16
    POSITIVE LOGITS
     Own
    0.20
    ÂĿ
    0.20
    astr
    0.19
    /'
    0.18
    ÂĢÂĻ
    0.18
     own
    0.16
    ãĤ¤ãĥ¤
    0.16
     been
    0.16
    tatus
    0.16
    icker
    0.15
    Act Density 0.777%

    No Known Activations