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

    Neuronpedia

    INDEX
    Explanations

    references to different countries, regional locations, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to countries and their relations or issues within a geopolitical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Blocks
    -0.65
    ï¸
    -0.65
    ocious
    -0.65
    java
    -0.65
    ength
    -0.63
     Nem
    -0.63
    ancy
    -0.62
     helm
    -0.59
    errors
    -0.58
    rang
    -0.58
    POSITIVE LOGITS
    psons
    0.74
    iland
    0.72
     embassy
    0.72
    GI
    0.71
     Postal
    0.70
     diplomat
    0.70
    ober
    0.68
    ensen
    0.68
     passports
    0.66
    OPE
    0.66
    Act Density 0.283%

    No Known Activations