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

    Neuronpedia

    INDEX
    Explanations

    expressions of welcome and hospitality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Spie
    -0.84
     devriez
    -0.77
    pageY
    -0.77
    uyasha
    -0.74
     VIAF
    -0.71
    UPI
    -0.70
    ukone
    -0.69
    luigi
    -0.67
    AdapterView
    -0.67
    p
    -0.67
    POSITIVE LOGITS
     welcome
    2.21
     welcomed
    1.94
     welcoming
    1.89
    welcome
    1.86
     Welcome
    1.84
     WELCOME
    1.84
     welcomes
    1.78
    elcome
    1.74
    Welcome
    1.69
    WELCOME
    1.69
    Act Density 0.050%

    No Known Activations