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

    Neuronpedia

    INDEX
    Explanations

    code comments containing specific characters or patterns

    oai_token-act-pair · gpt-3.5-turbo

    comments in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylum
    -0.98
    vertisement
    -0.84
    xual
    -0.84
    phrine
    -0.83
     tsunami
    -0.80
     satell
    -0.80
    edom
    -0.79
     livest
    -0.78
     tide
    -0.75
    ĺħ
    -0.74
    POSITIVE LOGITS
    ////////////////////////////////
    1.18
    ////////
    1.18
    ////////////////
    1.12
    ++++++++++++++++
    1.04
    ================================================================
    0.97
    wcsstore
    0.93
    ////
    0.93
     MARK
    0.92
     =================================================================
    0.91
    -->
    0.90
    Act Density 0.010%

    No Known Activations