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

    Neuronpedia

    INDEX
    Explanations

    code-related keywords and syntax patterns

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to programming language access modifiers and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orsi
    -0.89
    grain
    -0.82
    won
    -0.81
    hedon
    -0.80
    halla
    -0.77
    ieg
    -0.75
    ancock
    -0.74
    agin
    -0.74
    awed
    -0.73
    wig
    -0.73
    POSITIVE LOGITS
     bool
    1.19
     enum
    1.11
     boolean
    1.08
     void
    1.07
     Array
    0.95
     static
    0.94
     int
    0.93
     String
    0.91
     uint
    0.89
     string
    0.89
    Act Density 0.028%

    No Known Activations