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

    Neuronpedia

    INDEX
    Explanations

    expressions of welcome or greetings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    enumi
    -0.90
     initComponents
    -0.74
     Spie
    -0.74
    enumii
    -0.73
    tsburgh
    -0.72
    uyasha
    -0.71
     Tahoe
    -0.70
    icoot
    -0.69
     smtplib
    -0.66
    siers
    -0.65
    POSITIVE LOGITS
     welcome
    1.52
     Welcome
    1.38
     welcomed
    1.38
    WELCOME
    1.33
     WELCOME
    1.32
     welcoming
    1.31
    elcome
    1.30
    welcome
    1.30
    Welcome
    1.24
     welcomes
    1.22
    Act Density 0.006%

    No Known Activations