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

    Neuronpedia

    INDEX
    Explanations

    references to utility functions or tools in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.87
     CreateTagHelper
    -0.77
     sockaddr
    -0.73
    contentLoaded
    -0.73
    modelBuilder
    -0.69
    routeProvider
    -0.68
    DeleteBehavior
    -0.67
     JFrame
    -0.66
    RunWith
    -0.65
     Schindler
    -0.65
    POSITIVE LOGITS
    utils
    2.90
     utils
    2.55
    Utils
    2.50
     Utils
    2.16
     utility
    1.50
    Utilities
    1.41
     Utility
    1.40
     utilities
    1.35
    Utility
    1.34
     Utilities
    1.32
    Act Density 0.040%

    No Known Activations