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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitional phrases that indicate contrast or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    but versus whereas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.60
     AssemblyCulture
    -0.60
    nodoc
    -0.58
    MethodManager
    -0.55
    Personensuche
    -0.54
     nonUne
    -0.54
    Skocz
    -0.53
    bootstrapcdn
    -0.52
     EconPapers
    -0.52
    期刊论文
    -0.50
    POSITIVE LOGITS
    TED
    0.44
     اما
    0.42
     whereas
    0.42
     tačiau
    0.42
     tetapi
    0.41
    Whereas
    0.41
    而
    0.40
    CU
    0.40
    buss
    0.40
    But
    0.39
    Act Density 0.184%

    No Known Activations