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

    Neuronpedia

    INDEX
    Explanations

    phrases related to health risks and medical studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tern
    -0.15
    oku
    -0.15
    abet
    -0.15
     Krish
    -0.14
    one
    -0.14
    otyping
    -0.14
    ér
    -0.14
    ámara
    -0.14
     Dup
    -0.14
    ria
    -0.14
    POSITIVE LOGITS
    itung
    0.16
    ctest
    0.15
    oje
    0.14
    леж
    0.14
    (compact
    0.14
    eci
    0.13
    ä¼´
    0.13
    éĽ
    0.13
    ROUGH
    0.13
     gec
    0.13
    Act Density 1.032%

    No Known Activations