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

    Neuronpedia

    INDEX
    Explanations

    references to a specific person, often using pronouns or names

    oai_token-act-pair · gemini-2.0-flash

    German possessive pronouns

    np_token-act-pair-logits · gpt-4o-mini

    Pronouns and descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     his
    -2.91
     himself
    -2.88
    his
    -2.52
    himself
    -2.50
    彼の
    -2.09
    His
    -1.99
    彼は
    -1.95
     Himself
    -1.89
    彼が
    -1.88
     그의
    -1.80
    POSITIVE LOGITS
     ihrer
    0.78
     ihrem
    0.72
     &=&
    0.70
     ihren
    0.69
     ihre
    0.68
     their
    0.63
    &=&
    0.60
     Jej
    0.58
    &=&\
    0.56
     ihres
    0.56
    Act Density 7.001%

    No Known Activations