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

    Neuronpedia

    INDEX
    Explanations

    terminology related to chat systems and their integration with information retrieval and dialogue processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĥŀ
    -0.17
     kok
    -0.14
     impl
    -0.14
    roj
    -0.14
     gest
    -0.13
     cave
    -0.13
    ãĥĥãĥĹ
    -0.13
     flipping
    -0.13
     cheek
    -0.13
     PR
    -0.13
    POSITIVE LOGITS
    agement
    0.16
    оги
    0.15
     خشک
    0.15
    ona
    0.15
    باش
    0.15
    aise
    0.14
     maduras
    0.14
    oracle
    0.14
    oulder
    0.14
    conda
    0.14
    Act Density 0.004%

    No Known Activations