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

    Neuronpedia

    INDEX
    Explanations

    expressions of kindness and hospitality in social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     partagé
    -0.55
    enumi
    -0.53
     архивлан
    -0.52
     doskon
    -0.52
     disambiguazione
    -0.51
     Escolar
    -0.49
    ponym
    -0.49
     marriages
    -0.49
    ärin
    -0.47
     pamię
    -0.47
    POSITIVE LOGITS
     welcoming
    1.07
     welcome
    0.88
     welcomes
    0.85
     inviting
    0.81
     welcomed
    0.77
     invitation
    0.76
     hostility
    0.75
     ramah
    0.75
     hostile
    0.75
     Welcome
    0.75
    Act Density 0.090%

    No Known Activations