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

    Neuronpedia

    INDEX
    Explanations

    formal structures and processes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surrounding
    -0.16
    ERRU
    -0.14
    ndo
    -0.14
     mez
    -0.14
    ç°
    -0.13
    ãĤīãģĦ
    -0.13
    alu
    -0.13
    çıł
    -0.13
    ylko
    -0.13
    ι
    -0.13
    POSITIVE LOGITS
    omen
    0.16
    kl
    0.14
    imens
    0.14
    riage
    0.14
    exampleModal
    0.13
     Heck
    0.13
    airs
    0.13
    odule
    0.13
    kh
    0.13
    flare
    0.13
    Act Density 0.028%

    No Known Activations