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

    Neuronpedia

    INDEX
    Explanations

    numeric values embedded within a text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     nomine
    -0.70
     millenn
    -0.68
    theless
    -0.66
     deficit
    -0.66
    reau
    -0.64
     bulky
    -0.64
     beginners
    -0.63
     newcomers
    -0.63
    entimes
    -0.62
    ntil
    -0.62
    POSITIVE LOGITS
     partName
    1.24
    364
    0.94
    295
    0.90
    394
    0.89
    461
    0.88
    456
    0.87
    347
    0.87
    806
    0.87
    265
    0.86
    681
    0.86
    Act Density 0.102%

    No Known Activations