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

    Neuronpedia

    INDEX
    Explanations

    pronouns and possessive adjectives indicating relationships between people or entities

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

    pronouns and possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exp
    -0.35
    เช
    -0.34
     de
    -0.34
     cái
    -0.34
    ูล
    -0.33
     bu
    -0.32
     of
    -0.31
     שב
    -0.31
     từ
    -0.31
    sounding
    -0.30
    POSITIVE LOGITS
    Him
    0.83
     meille
    0.81
     Them
    0.76
    Them
    0.75
    them
    0.72
     Him
    0.71
     Himself
    0.71
     conmigo
    0.71
     THEM
    0.71
     them
    0.71
    Act Density 0.006%

    No Known Activations