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

    Neuronpedia

    INDEX
    Explanations

    words related to locations in Australia

    oai_token-act-pair · gpt-3.5-turbo

    references to Australia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FFER
    -0.70
    merce
    -0.68
     Speedway
    -0.64
    ullivan
    -0.63
    linger
    -0.63
    riad
    -0.62
     Hots
    -0.62
     Jobs
    -0.62
    elf
    -0.62
     Sawyer
    -0.60
    POSITIVE LOGITS
    ogy
    1.06
    ogical
    1.05
    ateral
    1.04
    tarians
    1.01
    tarian
    0.95
    isks
    0.94
    anguage
    0.93
    iberal
    0.90
    pha
    0.87
    pine
    0.86
    Act Density 0.018%

    No Known Activations