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

    Neuronpedia

    INDEX
    Explanations

    concepts and discussions centered around values, especially those related to love and family

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     teneur
    -0.56
     parallèle
    -0.55
     rédaction
    -0.54
     isomorphic
    -0.52
    ercito
    -0.52
     législation
    -0.52
     cláus
    -0.51
    illoin
    -0.50
     malheure
    -0.50
     المعيارى
    -0.49
    POSITIVE LOGITS
     happiness
    1.07
     freedom
    1.05
     creativity
    1.04
     love
    1.00
     joy
    0.98
     honesty
    0.97
     excellence
    0.96
     peace
    0.95
     innovation
    0.94
     purity
    0.94
    Act Density 0.633%

    No Known Activations