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

    Neuronpedia

    INDEX
    Explanations

    the term "Poly" with high activation values

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Watson
    -0.71
     Refuge
    -0.69
     Bauer
    -0.67
     keeper
    -0.64
     Redemption
    -0.62
     Byrd
    -0.62
     Lauder
    -0.61
     recall
    -0.60
     trove
    -0.60
    CRIP
    -0.60
    POSITIVE LOGITS
    gon
    1.41
    phony
    1.22
    morph
    1.21
    meric
    1.16
    chrome
    1.15
    mers
    1.14
    ester
    1.14
    nesia
    1.11
    mer
    1.08
    techn
    1.04
    Act Density 0.009%

    No Known Activations