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

    Neuronpedia

    INDEX
    Explanations

    terms related to duplicate data elimination in datasets

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

    Mentions removing duplicates or duplication

    np_acts-logits-general · gemini-2.0-flash

    removing duplicate entries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     isInitialized
    -0.55
    BeginInit
    -0.55
    EndInit
    -0.54
    sizeCache
    -0.54
     rând
    -0.50
    Autoritní
    -0.49
     yyl
    -0.48
     transfieras
    -0.46
     vielmehr
    -0.45
    Fö
    -0.45
    POSITIVE LOGITS
     duplicate
    1.41
     duplicates
    1.31
     duplicated
    1.17
    duplicate
    1.14
     Duplicate
    1.12
     missing
    1.11
     dup
    1.09
    Duplicate
    1.06
     duplication
    1.05
     overlaps
    1.03
    Act Density 1.159%

    No Known Activations