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

    Neuronpedia

    INDEX
    Explanations

    terms related to health risks and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĩаÑģ
    -0.15
    ROUT
    -0.14
    .Enqueue
    -0.14
    æľĪ
    -0.14
    umu
    -0.14
    شتر
    -0.14
     Hermes
    -0.14
    ιÏĩ
    -0.14
    ãĥijãĥ³
    -0.14
    ãĥĩãĥ«
    -0.13
    POSITIVE LOGITS
     death
    0.26
     deaths
    0.24
     mortality
    0.23
    Deaths
    0.22
     cause
    0.20
     leading
    0.20
    death
    0.20
     Death
    0.19
    Cause
    0.19
     burden
    0.19
    Act Density 0.035%

    No Known Activations