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

    Neuronpedia

    INDEX
    Explanations

    words that express emotions and sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DeleteBehavior
    -0.93
    انيف
    -0.86
    WillAppear
    -0.84
    parsedMessage
    -0.84
     auffi
    -0.82
    WebElementEntity
    -0.81
     Мексичка
    -0.79
    Personensuche
    -0.79
    expandindo
    -0.78
     ComVisible
    -0.77
    POSITIVE LOGITS
     ‘
    0.67
    ‘
    0.52
     thinking
    0.50
     way
    0.50
     [
    0.49
     love
    0.48
    zusch
    0.47
     «
    0.46
     sort
    0.46
     creative
    0.45
    Act Density 0.216%

    No Known Activations