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

    Neuronpedia

    INDEX
    Explanations

    references to AWS IAM (Identity and Access Management) roles and their permissions in policy documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    numerusform
    -0.64
    zeczy
    -0.60
    hoek
    -0.55
     Korn
    -0.55
    omla
    -0.54
    仰
    -0.53
     Ral
    -0.52
     ballast
    -0.52
    Korn
    -0.51
    CodedInputStream
    -0.49
    POSITIVE LOGITS
     Amazon
    1.69
    Amazon
    1.52
     amazon
    1.44
     AMAZON
    1.32
    amazon
    1.18
     AWS
    1.16
    AMAZ
    1.10
     Amaz
    1.09
    AWS
    1.07
     Kindle
    1.02
    Act Density 0.266%

    No Known Activations