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

    Neuronpedia

    INDEX
    Explanations

    terms related to numerical values or metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lee
    -0.15
    rick
    -0.14
    ils
    -0.14
    bul
    -0.14
    peare
    -0.14
    eyi
    -0.14
    riz
    -0.14
    ic
    -0.14
    ble
    -0.13
    places
    -0.13
    POSITIVE LOGITS
    é¹
    0.14
    cobra
    0.14
    ëĤĺëĿ¼
    0.14
    à¹īà¸Ń
    0.14
    igu
    0.14
    WebHost
    0.14
    zano
    0.14
    /-
    0.14
     */↵↵↵↵
    0.13
    ฺ
    0.13
    Act Density 0.015%

    No Known Activations