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

    Neuronpedia

    INDEX
    Explanations

    expressions of pride and self-satisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Suara
    -0.70
     transfieras
    -0.68
    OPSIS
    -0.65
    FormTagHelper
    -0.64
     <=",
    -0.61
     resourceCulture
    -0.59
    atherapy
    -0.59
    ">//
    -0.59
     VES
    -0.57
     contextLoads
    -0.56
    POSITIVE LOGITS
     proud
    2.65
    proud
    2.40
     pride
    2.34
    Proud
    2.23
     Proud
    2.18
     orgull
    2.14
    pride
    1.97
     proudly
    1.95
     stolz
    1.95
     orgullo
    1.92
    Act Density 0.072%

    No Known Activations