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

    Neuronpedia

    INDEX
    Explanations

    programming code snippets

    oai_token-act-pair · gpt-3.5-turbo

    constructs related to programming functions and classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebook
    -0.76
    Sov
    -0.76
    mberg
    -0.76
    Anth
    -0.75
    sung
    -0.73
    uploads
    -0.73
    qus
    -0.73
    assic
    -0.70
    byn
    -0.70
    Ku
    -0.70
    POSITIVE LOGITS
     bool
    1.03
     boolean
    1.00
    uint
    0.95
     uint
    0.94
     override
    0.93
     const
    0.91
     /**
    0.89
     struct
    0.88
     void
    0.83
     int
    0.83
    Act Density 0.120%

    No Known Activations