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

    Neuronpedia

    INDEX
    Explanations

    words related to straightforwardness and simplicity

    oai_token-act-pair · gpt-3.5-turbo

    the term "simple" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.80
    âĹ¼
    -0.74
    raints
    -0.71
    ingle
    -0.70
    hips
    -0.70
    vance
    -0.70
    inburgh
    -0.68
     extensively
    -0.68
    MIC
    -0.67
     skelet
    -0.67
    POSITIVE LOGITS
    tons
    1.22
    wallet
    0.99
    minded
    0.92
    json
    0.89
     arithmetic
    0.86
     straightforward
    0.81
     syrup
    0.81
    ified
    0.79
    coded
    0.79
    ton
    0.79
    Act Density 0.019%

    No Known Activations