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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of interpretation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ey
    -0.19
    readcr
    -0.18
    acre
    -0.18
    ughter
    -0.16
    /is
    -0.15
    lund
    -0.15
    askan
    -0.15
    ------------
    -0.14
    clare
    -0.14
    æ¡IJ
    -0.14
    POSITIVE LOGITS
    ãĤ¿ãĥ«
    0.17
    ural
    0.15
    cad
    0.15
    мов
    0.15
    urally
    0.14
    reuse
    0.14
    ëĭ¤
    0.14
    nock
    0.14
    angular
    0.14
    ative
    0.13
    Act Density 0.054%

    No Known Activations