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

    Neuronpedia

    INDEX
    Explanations

    references to Australia and its related contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Erie
    -0.77
     Morin
    -0.76
     Berks
    -0.75
     Spill
    -0.75
    σσ
    -0.69
    </b>
    -0.68
     Gef
    -0.68
    ="#
    -0.65
    Spill
    -0.65
     Schenectady
    -0.65
    POSITIVE LOGITS
     Australia
    1.48
     Australian
    1.45
     Australians
    1.42
    Australia
    1.41
     australian
    1.36
     Aussie
    1.34
     AUSTRALIA
    1.30
    ALIAN
    1.30
    Australian
    1.27
    australia
    1.25
    Act Density 0.017%

    No Known Activations