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

    Neuronpedia

    INDEX
    Explanations

    words with diacritical marks, specifically the character "Ã"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "São" and its related inflections or variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itionally
    -0.74
    guide
    -0.73
    PAR
    -0.72
    nut
    -0.71
    lake
    -0.70
    models
    -0.69
    IPS
    -0.69
    picture
    -0.69
    nuts
    -0.68
    ritic
    -0.68
    POSITIVE LOGITS
     Paulo
    1.39
    ão
    1.38
    vernment
    1.02
     Janeiro
    0.97
     Bras
    0.86
    ð
    0.85
     Lumpur
    0.84
     José
    0.82
     Sao
    0.81
     Grande
    0.80
    Act Density 0.008%

    No Known Activations