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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to different types of people or characters with specific traits

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.83
    yss
    -0.81
    inventoryQuantity
    -0.71
    abella
    -0.70
    dL
    -0.66
    ãĤ¦ãĤ¹
    -0.66
    azeera
    -0.66
     Accuracy
    -0.66
     Regulation
    -0.65
     GOODMAN
    -0.65
    POSITIVE LOGITS
     surrounded
    1.22
     sandwic
    1.17
     whose
    1.03
     devoid
    1.00
     flanked
    0.98
     riddled
    0.97
     circa
    0.97
     crammed
    0.96
     sprinkled
    0.92
     striving
    0.89
    Act Density 0.536%

    No Known Activations