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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names of people or organizations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    orically
    -1.03
    apo
    -1.01
    adden
    -1.01
    antics
    -0.99
    abol
    -0.98
    SON
    -0.96
    abulary
    -0.96
    manac
    -0.96
    utenberg
    -0.92
    ensible
    -0.92
    POSITIVE LOGITS
     flanked
    1.27
     pictured
    1.23
     portraits
    1.18
     photographed
    1.14
     paw
    1.04
     photos
    1.01
     Ruk
    1.01
     KD
    1.01
     IMAGES
    1.00
     Courtesy
    0.97
    Act Density 0.717%

    No Known Activations