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

    Neuronpedia

    INDEX
    Explanations

    concepts related to guidance and structure in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igin
    -0.15
    ãĥ¼ãĥ«ãĥī
    -0.15
     Tato
    -0.14
    dera
    -0.14
    ughs
    -0.14
    imilar
    -0.14
    zcze
    -0.14
    ctal
    -0.14
    chas
    -0.14
     similarly
    -0.13
    POSITIVE LOGITS
     ấy
    0.19
    -ÑĤо
    0.18
     tersebut
    0.17
    ä¹ĥ
    0.15
    ukan
    0.14
    rokes
    0.14
    ingham
    0.14
    erness
    0.14
    ertia
    0.14
     itself
    0.13
    Act Density 0.365%

    No Known Activations