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

    Neuronpedia

    INDEX
    Explanations

    names of candies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    phrine
    -0.63
    chron
    -0.63
    iets
    -0.60
    yon
    -0.57
    productive
    -0.56
     plur
    -0.56
     Luxem
    -0.55
    shire
    -0.55
    lihood
    -0.54
     Peoples
    -0.53
    POSITIVE LOGITS
     cane
    0.95
     candy
    0.86
    strip
    0.85
    mallow
    0.84
    bucks
    0.81
     gum
    0.75
     wra
    0.75
    weet
    0.75
    corn
    0.74
    pole
    0.73
    Act Density 5.060%

    No Known Activations