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

    Neuronpedia

    INDEX
    Explanations

    terms related to cleaning and hygiene activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.78
     [
    -0.70
     “
    -0.69
    <eos>
    -0.65
      
    -0.65
     (
    -0.64
     I
    -0.61
    ↵↵
    -0.60
     \
    -0.60
    ,
    -0.59
    POSITIVE LOGITS
     cleaning
    1.42
     cleans
    1.39
     Cleaning
    1.36
     cleanliness
    1.35
    Cleaning
    1.33
     CLEANING
    1.32
     cleaners
    1.30
     Cleaners
    1.27
     Efq
    1.21
    cleaning
    1.20
    Act Density 0.245%

    No Known Activations