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

    Neuronpedia

    INDEX
    Explanations

    corrections and updates within text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.72
    forms
    -0.71
    é¾įå¥ij士
    -0.70
    Frameworks
    -0.70
    ateurs
    -0.69
    vironments
    -0.69
    edIn
    -0.68
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
    æ©
    -0.67
    iors
    -0.65
    POSITIVE LOGITS
     typo
    1.21
     corrected
    1.16
    Clar
    1.01
     Updated
    0.97
     clarification
    0.95
     commenter
    0.95
     Correction
    0.90
    PDATED
    0.90
     Added
    0.88
     deleted
    0.88
    Act Density 1.402%

    No Known Activations