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

    Neuronpedia

    INDEX
    Explanations

    discussions on hypocrisy and moral dilemmas in social and political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĨµ
    -0.17
    emoc
    -0.15
    ä»ģ
    -0.15
    oubles
    -0.15
    adic
    -0.14
    ieu
    -0.14
    orraine
    -0.14
    ãĥķãĤ§
    -0.14
     nam
    -0.14
    eldom
    -0.14
    POSITIVE LOGITS
     soak
    0.15
    λιά
    0.13
    zia
    0.13
     TCHAR
    0.13
     reput
    0.13
     cousin
    0.13
     Plat
    0.13
     æŀ
    0.13
     Coord
    0.13
    èĪ
    0.13
    Act Density 1.293%

    No Known Activations