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

    Neuronpedia

    INDEX
    Explanations

    phrases related to experimental results and performance metrics in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zte
    -0.16
    cimal
    -0.15
     Mods
    -0.14
    γον
    -0.14
     mods
    -0.14
    HELL
    -0.14
    опаÑģ
    -0.14
     pokoj
    -0.14
    wich
    -0.14
    ÄĽti
    -0.13
    POSITIVE LOGITS
     performance
    0.23
    performance
    0.19
     results
    0.19
     Performance
    0.18
    æĢ§èĥ½
    0.16
    Performance
    0.16
     improvement
    0.15
     performan
    0.15
     PERFORMANCE
    0.15
    results
    0.15
    Act Density 0.093%

    No Known Activations