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

    Neuronpedia

    INDEX
    Explanations

    questions in a structured format with specific keywords

    oai_token-act-pair · gpt-3.5-turbo

    questions and context brackets commonly used in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oche
    -0.81
    formed
    -0.70
    ãĤ§
    -0.68
    igans
    -0.64
    itol
    -0.63
    rawdownloadcloneembedreportprint
    -0.63
    ahime
    -0.63
     Revel
    -0.61
    Constructed
    -0.60
    comb
    -0.60
    POSITIVE LOGITS
     Explain
    1.01
     Whats
    0.84
     Lastly
    0.77
     Would
    0.77
     Did
    0.76
     Could
    0.76
     Does
    0.76
    How
    0.76
     How
    0.74
     WHAT
    0.74
    Act Density 0.121%

    No Known Activations