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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of cleaning

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

    cleaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Murdoch
    -0.59
     valueForKey
    -0.53
     relationship
    -0.53
     moment
    -0.51
     {*}
    -0.48
    DataObject
    -0.48
     hormone
    -0.47
     characteristic
    -0.47
     third
    -0.46
     xPos
    -0.46
    POSITIVE LOGITS
    cleaned
    1.30
    Clean
    1.28
     cleaned
    1.26
    clean
    1.22
    Cleaning
    1.21
     CLEAN
    1.21
     Clean
    1.20
     Cleaning
    1.17
    CLEAN
    1.16
    cleaner
    1.15
    Act Density 0.006%

    No Known Activations