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

    Neuronpedia

    INDEX
    Explanations

    code snippets containing comments or URLs

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of comment syntax in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylum
    -0.86
    edom
    -0.85
     tsunami
    -0.84
    phrine
    -0.83
    ĺħ
    -0.83
     tide
    -0.81
    vertisement
    -0.79
     satell
    -0.77
     livest
    -0.74
     staggered
    -0.73
    POSITIVE LOGITS
    ////////
    1.16
    ////////////////
    1.12
    wcsstore
    1.11
    ////////////////////////////////
    1.08
    ////
    1.05
    ++++++++++++++++
    1.03
    ================================================================
    0.95
    ERROR
    0.91
    Applications
    0.90
    TL
    0.88
    Act Density 0.008%

    No Known Activations