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

    Neuronpedia

    INDEX
    Explanations

    phrases questioning the role and beliefs of certain individuals regarding public welfare and taxation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     вин
    -0.15
    ¼
    -0.15
    365
    -0.15
    adal
    -0.15
    amina
    -0.15
    icode
    -0.14
    BF
    -0.14
    .mit
    -0.14
    esz
    -0.14
    bcm
    -0.14
    POSITIVE LOGITS
     Libertarian
    0.29
     libertarian
    0.26
     libert
    0.23
     Libert
    0.23
     laisse
    0.22
     Liberty
    0.20
     liberty
    0.20
    Freedom
    0.17
     Freedom
    0.16
    Lib
    0.16
    Act Density 0.104%

    No Known Activations