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

    Neuronpedia

    INDEX
    Explanations

    concepts related to societal and political power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     miêu
    -0.17
    echan
    -0.16
    ÑĨÑĸоналÑĮ
    -0.14
    /***************************************************************************↵
    -0.14
     Adolf
    -0.14
    leneck
    -0.14
    .mutable
    -0.14
    ÏĩÏĮ
    -0.13
     Pelosi
    -0.13
    utorial
    -0.13
    POSITIVE LOGITS
     soci
    0.24
     professor
    0.19
     CLR
    0.18
     Professor
    0.18
     Fuk
    0.18
     Nass
    0.18
     historian
    0.18
     Prof
    0.17
    538
    0.17
     Ori
    0.17
    Act Density 0.271%

    No Known Activations