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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or coding syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ding
    -0.16
    ilit
    -0.15
    ylie
    -0.15
    IJèĹı
    -0.14
     neutral
    -0.14
    ÑĢалÑĮ
    -0.14
    yah
    -0.13
    dings
    -0.13
    aber
    -0.13
    'Ñı
    -0.13
    POSITIVE LOGITS
    erif
    0.17
    /interfaces
    0.17
    ινε
    0.15
    ÑĢиÑģÑĤи
    0.15
     McCart
    0.14
     Hlav
    0.14
     vÃŃde
    0.14
    chia
    0.14
    eof
    0.14
    ุà¸Ĺà¸ĺ
    0.14
    Act Density 0.005%

    No Known Activations