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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various items being sold or marketed

    oai_token-act-pair · gpt-3.5-turbo

    terms related to regulated products and commodities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     repetition
    -0.59
     adversary
    -0.59
    ULT
    -0.59
     Hacker
    -0.58
     Cats
    -0.57
     rapport
    -0.57
     onlook
    -0.56
    cknow
    -0.55
     coincidence
    -0.54
     rivalry
    -0.52
    POSITIVE LOGITS
     cheaply
    1.06
     freely
    0.97
     abroad
    0.95
     efficiently
    0.89
     safely
    0.87
     directly
    0.85
    soever
    0.82
     securely
    0.81
    coins
    0.80
     without
    0.79
    Act Density 0.512%

    No Known Activations