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

    Neuronpedia

    INDEX
    Explanations

    references to international relations and geopolitical entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oningen
    -0.16
    678
    -0.15
     Gust
    -0.15
    936
    -0.14
    fern
    -0.14
    ικο
    -0.14
    CREMENT
    -0.14
    ald
    -0.14
    .NotNil
    -0.14
    376
    -0.14
    POSITIVE LOGITS
    VO
    0.17
     Scot
    0.16
    FILE
    0.16
    _VO
    0.15
    eeper
    0.15
    utos
    0.15
     vo
    0.15
     VO
    0.15
     Hai
    0.14
    .modules
    0.14
    Act Density 0.004%

    No Known Activations