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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal activities and legal proceedings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ń·
    -0.65
     Canaver
    -0.64
     shroud
    -0.62
    ÃįÃį
    -0.61
    seys
    -0.61
     bells
    -0.60
    MENTS
    -0.59
     Restrict
    -0.59
    kson
    -0.58
     Tant
    -0.58
    POSITIVE LOGITS
    generation
    1.19
    degree
    1.12
    class
    1.03
    chance
    1.02
    round
    0.99
    ever
    0.98
    year
    0.98
    hand
    0.97
    century
    0.97
    tier
    0.97
    Act Density 0.017%

    No Known Activations