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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and organizations within a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hund
    -0.18
    µ
    -0.18
     Alive
    -0.17
     Urs
    -0.15
    çľģ
    -0.15
    ooled
    -0.15
    aukee
    -0.14
     ÐĴаÑĢ
    -0.14
    SCO
    -0.14
    dae
    -0.14
    POSITIVE LOGITS
     Deb
    0.24
    deb
    0.23
     Pavel
    0.21
     Moy
    0.21
     Prod
    0.21
     Mond
    0.21
     Prot
    0.21
     Ferd
    0.21
     Sark
    0.20
     Dut
    0.19
    Act Density 0.019%

    No Known Activations