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

    Neuronpedia

    INDEX
    Explanations

    references to systemic issues and critiques in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     çħ
    -0.16
    urve
    -0.15
    ê°IJ
    -0.15
    kem
    -0.15
    вÑĥ
    -0.15
     Decomp
    -0.14
    atta
    -0.14
    UNUSED
    -0.14
     Beled
    -0.13
     /*!
    -0.13
    POSITIVE LOGITS
     system
    0.28
    system
    0.23
    ystem
    0.22
    -system
    0.20
     System
    0.17
     ÑģиÑģÑĤема
    0.17
     système
    0.17
     reform
    0.17
    anity
    0.16
    ystems
    0.16
    Act Density 0.209%

    No Known Activations