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

    Neuronpedia

    INDEX
    Explanations

    phrases involving controlled substances or processes

    oai_token-act-pair · gpt-3.5-turbo

    references to controlled substances or regulations surrounding them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĭ
    -0.82
     Honour
    -0.80
     Kinnikuman
    -0.74
    eeks
    -0.73
    alos
    -0.73
    elt
    -0.70
     Thieves
    -0.70
    scribe
    -0.66
    é¾įåĸļ士
    -0.66
     Blessed
    -0.65
    POSITIVE LOGITS
     controlled
    1.03
    poons
    0.88
     contro
    0.83
     substances
    0.78
    uled
    0.76
    controlled
    0.75
     territ
    0.75
    kefeller
    0.74
     demolition
    0.74
     runaway
    0.73
    Act Density 0.040%

    No Known Activations