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

    Neuronpedia

    INDEX
    Explanations

    expressions of appreciation and gratitude

    oai_token-act-pair · gpt-3.5-turbo

    expressions of appreciation and affection towards an individual or community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edit
    -0.67
    toggle
    -0.67
     guiActiveUn
    -0.64
    hot
    -0.62
     Abstract
    -0.61
     dod
    -0.61
    Abstract
    -0.61
    ãĥĥãĥĪ
    -0.60
    Alien
    -0.59
    aded
    -0.58
    POSITIVE LOGITS
     courageous
    0.87
     compassionate
    0.85
     stewards
    0.82
     philanthrop
    0.82
     sacrific
    0.81
     multicultural
    0.79
     comr
    0.76
     excellence
    0.76
    cellence
    0.76
     transformative
    0.75
    Act Density 2.049%

    No Known Activations