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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emotional expressions and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aján
    -0.51
     képes
    -0.51
     législation
    -0.50
     planète
    -0.48
    SqlDataReader
    -0.48
    biendo
    -0.47
     scène
    -0.47
     متعلقه
    -0.47
    nativeElement
    -0.46
    ългар
    -0.46
    POSITIVE LOGITS
     creativity
    0.87
     warmth
    0.79
     flexibility
    0.78
     accuracy
    0.78
     stability
    0.77
     elegance
    0.76
     resilience
    0.76
     strength
    0.76
     purity
    0.75
     reliability
    0.75
    Act Density 0.408%

    No Known Activations