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

    Neuronpedia

    INDEX
    Explanations

    phrases related to removing duplicates

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

    Removal of duplicates

    np_acts-logits-general · gemini-2.0-flash

    removing duplicates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fprintf
    -0.49
     sempre
    -0.48
     rând
    -0.47
     vielmehr
    -0.45
    zenio
    -0.45
    Risultati
    -0.43
    sizeCache
    -0.43
    Delimited
    -0.43
    ście
    -0.43
     mesi
    -0.42
    POSITIVE LOGITS
     duplicate
    1.76
     duplicates
    1.64
     duplicated
    1.47
     Duplicate
    1.44
     redundant
    1.41
    duplicate
    1.39
     duplication
    1.38
     dup
    1.30
    Duplicate
    1.27
    dup
    1.21
    Act Density 1.116%

    No Known Activations