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

    Neuronpedia

    INDEX
    Explanations

    concepts and themes related to universality and universal rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SG
    -0.15
    lying
    -0.14
    spi
    -0.14
    óln
    -0.14
    .authorization
    -0.14
    chen
    -0.14
    ieval
    -0.14
     latter
    -0.14
    abras
    -0.13
    bara
    -0.13
    POSITIVE LOGITS
    -wide
    0.17
    -scale
    0.16
    chg
    0.15
    å®Ļ
    0.14
    -sized
    0.14
    ized
    0.14
    weit
    0.14
    errupt
    0.13
    gent
    0.13
    enties
    0.13
    Act Density 0.029%

    No Known Activations