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

    Neuronpedia

    INDEX
    Explanations

    references to anti-establishment movements and ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bjerg
    -0.15
     æ¬
    -0.15
    adu
    -0.15
    esz
    -0.15
    Interpreter
    -0.15
    qn
    -0.15
     pew
    -0.14
    à¹īà¸Ńà¸ĩ
    -0.14
    бав
    -0.14
    ãģĸ
    -0.14
    POSITIVE LOGITS
     anarchist
    0.32
     anarchists
    0.31
     anarch
    0.28
     Libertarian
    0.21
     libertarian
    0.19
     Libert
    0.19
     underground
    0.17
     decentral
    0.17
     Vegan
    0.16
     libert
    0.16
    Act Density 0.026%

    No Known Activations