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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to the term "Knights"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    PROV
    -0.68
    aciously
    -0.66
    advert
    -0.64
    perature
    -0.61
    mble
    -0.61
    ãĤ¨ãĥ«
    -0.61
    gel
    -0.60
    essage
    -0.59
    à
    -0.59
    ience
    -0.59
    POSITIVE LOGITS
     Templar
    1.25
    mares
    1.08
     Templ
    1.05
     Knights
    1.03
    hip
    0.85
     Radiant
    0.84
    mare
    0.78
    aido
    0.78
    warm
    0.78
    doms
    0.77
    Act Density 0.013%

    No Known Activations