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

    Neuronpedia

    INDEX
    Explanations

    entities related to locations and individual names

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.81
     favorably
    -0.81
     flavorful
    -0.80
     colorless
    -0.79
     odors
    -0.78
     theater
    -0.74
     multicolored
    -0.73
     favors
    -0.73
     Ameri
    -0.73
    Colorful
    -0.72
    POSITIVE LOGITS
     Australian
    1.24
    1.23
     Australia
    1.18
     Australians
    1.09
    Australian
    1.06
     Sydney
    1.05
     Queensland
    1.04
     Melbourne
    1.02
     NSW
    1.00
    Australia
    0.97
    Act Density 0.357%

    No Known Activations