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

    Neuronpedia

    INDEX
    Explanations

    keywords related to health, safety, and research topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odge
    -0.16
    actus
    -0.15
    otine
    -0.15
    ubbo
    -0.14
    rete
    -0.14
    ستاÙĨ
    -0.14
    conc
    -0.14
    allen
    -0.14
    801
    -0.14
    ford
    -0.14
    POSITIVE LOGITS
    .yy
    0.19
    ÙĬÙĪÙĨ
    0.17
    ipes
    0.17
    ensem
    0.16
    çĩ
    0.15
    ços
    0.14
     dignity
    0.14
    /documentation
    0.14
    üzel
    0.13
    à¹ģส
    0.13
    Act Density 0.034%

    No Known Activations