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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to dirtiness

    oai_token-act-pair · gpt-3.5-turbo

    the word "dirty" in various contexts related to messiness or unethical behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.96
    iphate
    -0.95
    HCR
    -0.92
    ĸļ
    -0.84
    mare
    -0.81
    uther
    -0.81
    ajor
    -0.77
    hari
    -0.77
    doms
    -0.74
    ommel
    -0.73
    POSITIVE LOGITS
     laundry
    0.99
     dirty
    0.95
     linen
    0.92
    dirty
    0.85
     mole
    0.84
     cleaner
    0.82
    clean
    0.75
     diapers
    0.75
     rotten
    0.74
     diaper
    0.74
    Act Density 0.011%

    No Known Activations