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

    Neuronpedia

    INDEX
    Explanations

    Spanish words with accent marks

    oai_token-act-pair · gpt-3.5-turbo

    the character "á" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pistons
    -0.76
     FedEx
    -0.67
     Mills
    -0.66
     Lump
    -0.65
     desk
    -0.65
     Muscle
    -0.64
     PF
    -0.63
     spotting
    -0.63
     Sears
    -0.63
     MIL
    -0.61
    POSITIVE LOGITS
    á
    4.18
    án
    2.42
    ás
    2.27
    ÃŃ
    2.22
    ú
    2.05
    ó
    2.03
    Ãł
    2.02
    Ã
    1.64
    ÃŃn
    1.62
    é
    1.62
    Act Density 0.013%

    No Known Activations