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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or requests for help

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

    expressing appreciation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.51
    ammans
    -0.45
    Sdk
    -0.42
     Zaw
    -0.40
    drawText
    -0.39
     بوت
    -0.39
    Executives
    -0.38
    getRow
    -0.38
    CLS
    -0.37
    ByVersion
    -0.37
    POSITIVE LOGITS
     appreciate
    0.59
    Appreciate
    0.59
     Appreciate
    0.58
    InjectAttribute
    0.54
    setopt
    0.53
     Appreciation
    0.50
     appreciates
    0.50
     appreciated
    0.49
    Agrade
    0.49
    reciate
    0.49
    Act Density 0.009%

    No Known Activations