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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "read" and related phrases suggesting further reading or exploration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itis
    -0.17
    ñ
    -0.15
    à¸²à¸ľ
    -0.15
     blind
    -0.14
    amet
    -0.14
    ãĥ§
    -0.14
    ìķ¼
    -0.14
    Reader
    -0.14
     sạch
    -0.14
     remembered
    -0.13
    POSITIVE LOGITS
    illac
    0.15
    ress
    0.15
    inet
    0.15
    ynet
    0.15
    afort
    0.14
    коÑĤ
    0.14
    mission
    0.14
    ainer
    0.14
    urette
    0.14
    cki
    0.14
    Act Density 0.021%

    No Known Activations