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

    Neuronpedia

    INDEX
    Explanations

    terms related to hospitality and welcoming interactions

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

    welcoming guests and hospitality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     problem
    -0.39
     disease
    -0.39
     gré
    -0.39
     missing
    -0.38
     overhaul
    -0.36
    tierrez
    -0.36
     model
    -0.36
     unreliable
    -0.36
     med
    -0.35
     Newmarket
    -0.35
    POSITIVE LOGITS
     welcoming
    0.99
     hospitable
    0.88
     hospitality
    0.88
     welcome
    0.82
     welcomes
    0.82
    accueil
    0.81
     welcomed
    0.80
     bienvenida
    0.79
    welcome
    0.76
     Hospitality
    0.76
    Act Density 0.023%

    No Known Activations