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

    Neuronpedia

    INDEX
    Explanations

    actions associated with cleaning and maintenance procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    binant
    -0.55
     Stallion
    -0.53
    Tembelea
    -0.53
    querade
    -0.52
    Adder
    -0.52
     Infrastruktur
    -0.50
    kriegs
    -0.48
     GenerationType
    -0.47
     Insomnia
    -0.47
    vori
    -0.47
    POSITIVE LOGITS
     cleaning
    0.95
     cleans
    0.85
    cleaning
    0.81
     cleaner
    0.78
     Cleaning
    0.76
    Cleaning
    0.76
     wiping
    0.74
     cleansing
    0.73
     cleaners
    0.73
     scrubbing
    0.73
    Act Density 0.277%

    No Known Activations