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

    Neuronpedia

    INDEX
    Explanations

    definite articles and prepositions in multiple languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pyrr
    -0.63
     înd
    -0.58
     Limoges
    -0.57
     Ibero
    -0.55
     norman
    -0.55
     primario
    -0.55
     Gatsby
    -0.55
    Bers
    -0.54
    achten
    -0.54
     negru
    -0.54
    POSITIVE LOGITS
    MessageOf
    0.96
    بوابة
    0.96
     ofthe
    0.92
    Portale
    0.89
     del
    0.89
    ủa
    0.88
     the
    0.87
     du
    0.86
     của
    0.85
    ']=$
    0.85
    Act Density 0.017%

    No Known Activations