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

    Neuronpedia

    INDEX
    Explanations

    markers indicating high value or significance, such as important nouns and descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abez
    -0.15
    (
    -0.14
     ç¡
    -0.14
     exh
    -0.14
    aye
    -0.14
    cai
    -0.13
     (
    -0.13
    BE
    -0.13
     Capital
    -0.13
     IN
    -0.13
    POSITIVE LOGITS
    avou
    0.17
    'options
    0.15
    782
    0.15
     зов
    0.14
    ISCO
    0.14
    SSION
    0.14
    prak
    0.14
    èĸ¦
    0.13
     !***
    0.13
    reet
    0.13
    Act Density 0.005%

    No Known Activations