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

    Neuronpedia

    INDEX
    Explanations

    the letter "e" occurring as a single token

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ekster
    -0.78
     pymongo
    -0.69
    scalatest
    -0.68
    Przyp
    -0.67
     Alamofire
    -0.67
    bouncycastle
    -0.65
    Vaata
    -0.63
    Eksteraj
    -0.63
    Leírás
    -0.62
    testng
    -0.62
    POSITIVE LOGITS
     scrat
    1.06
     disagre
    1.05
     maneu
    1.01
     increa
    1.01
     intersper
    1.00
     impra
    0.99
     accla
    0.96
     suscep
    0.96
     inev
    0.95
     disgra
    0.93
    Act Density 0.048%

    No Known Activations