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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and numerical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ราย
    -0.16
    kah
    -0.16
    åł
    -0.14
    ermann
    -0.14
     ìļ°
    -0.14
    ands
    -0.14
    kes
    -0.13
     åł
    -0.13
    ICODE
    -0.13
    wers
    -0.13
    POSITIVE LOGITS
    alue
    0.20
    жа
    0.17
    quin
    0.14
    isco
    0.14
    OND
    0.14
    .pol
    0.14
     пÑĢиб
    0.14
    (predicate
    0.14
    ampus
    0.13
    venta
    0.13
    Act Density 0.001%

    No Known Activations