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

    Neuronpedia

    INDEX
    Explanations

    topics or keywords related to various categories such as government, politics, health, and celebrations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    otos
    -0.75
    ript
    -0.74
    termin
    -0.68
    Completed
    -0.64
     pent
    -0.62
    yrus
    -0.62
    jen
    -0.60
    coat
    -0.59
    atten
    -0.58
     ende
    -0.58
    POSITIVE LOGITS
    Topics
    0.87
     Include
    0.77
    matter
    0.74
    htaking
    0.70
    afety
    0.65
    ource
    0.65
     Topic
    0.65
     EVENT
    0.64
    encies
    0.63
    Questions
    0.63
    Act Density 0.028%

    No Known Activations