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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to happiness and positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "happy" or related terms

    np_acts-logits-general · gemini-2.0-flash

    happy phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mengen
    -0.52
     كمان
    -0.51
    |}{}
    -0.50
    inai
    -0.47
    ailleurs
    -0.46
    welche
    -0.46
     AssemblyCompany
    -0.46
    ništ
    -0.45
    ταν
    -0.45
    chige
    -0.45
    POSITIVE LOGITS
    HAPPY
    1.05
     happy
    1.01
     HAPPY
    0.97
     Happy
    0.94
    happy
    0.94
    Happy
    0.91
    webElementXpaths
    0.85
     happier
    0.84
     Happ
    0.83
     feliz
    0.83
    Act Density 0.050%

    No Known Activations