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

    Neuronpedia

    INDEX
    Explanations

    attribute assignments in XML code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annel
    -0.15
    kim
    -0.15
     correct
    -0.14
    μή
    -0.14
    anke
    -0.14
    ideo
    -0.14
    subpackage
    -0.14
    Sphere
    -0.14
    år
    -0.14
    amework
    -0.14
    POSITIVE LOGITS
    ongyang
    0.16
     Patt
    0.15
    ://%
    0.15
    312
    0.14
    خرج
    0.14
    ylie
    0.14
    ator
    0.13
     pData
    0.13
    ibal
    0.13
    _preference
    0.13
    Act Density 0.001%

    No Known Activations