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

    Neuronpedia

    INDEX
    Explanations

    the attribution of authorship or credits in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bc
    -0.17
    ulative
    -0.16
    emony
    -0.15
     bulk
    -0.15
    allen
    -0.14
    bulk
    -0.14
     per
    -0.14
    emme
    -0.14
    ATO
    -0.14
     penny
    -0.14
    POSITIVE LOGITS
    teri
    0.17
    831
    0.17
    é±
    0.16
    istrovstvÃŃ
    0.16
    CONDS
    0.15
    GORITH
    0.15
     ?>"/>↵
    0.14
    ÑĸÑĹв
    0.14
    ÙĪÙĨØ©
    0.14
    usch
    0.14
    Act Density 0.010%

    No Known Activations