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

    Neuronpedia

    INDEX
    Explanations

    words in Portuguese

    oai_token-act-pair · gpt-3.5-turbo

    the name and references to Brazilian locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itionally
    -0.88
    nut
    -0.84
    nuts
    -0.80
    iflower
    -0.78
    wig
    -0.74
    mable
    -0.73
    lake
    -0.73
     directions
    -0.73
    arily
    -0.73
    IFIC
    -0.73
    POSITIVE LOGITS
     Paulo
    1.38
    ão
    1.12
    vernment
    0.94
     Janeiro
    0.93
     José
    0.86
     Jiu
    0.85
     Grande
    0.84
    ItemTracker
    0.82
    ð
    0.82
     Lumpur
    0.82
    Act Density 0.017%

    No Known Activations