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

    Neuronpedia

    INDEX
    Explanations

    terms related to societal issues and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irs
    -0.16
    ilen
    -0.16
    artz
    -0.16
    olk
    -0.15
    ich
    -0.15
    Ïģιά
    -0.15
    iting
    -0.15
     dönemde
    -0.14
    iele
    -0.14
    alt
    -0.14
    POSITIVE LOGITS
    uhl
    0.15
    licant
    0.15
    529
    0.14
    ynet
    0.14
    865
    0.14
    utzer
    0.14
    fuscated
    0.13
     Stap
    0.13
    yny
    0.13
    HAV
    0.13
    Act Density 0.115%

    No Known Activations