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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical notation and proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Cast
    -0.15
    sah
    -0.15
    äºĭ
    -0.14
    rž
    -0.14
    arah
    -0.13
    itchens
    -0.13
    ì¡°
    -0.13
    _$_
    -0.13
     sáng
    -0.13
    __$
    -0.13
    POSITIVE LOGITS
    ledo
    0.17
    589
    0.16
    ine
    0.16
    {}{↵
    0.16
     #'
    0.15
    antt
    0.15
    [][
    0.14
    stile
    0.14
     Bien
    0.14
    *[
    0.14
    Act Density 0.131%

    No Known Activations