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

    Neuronpedia

    INDEX
    Explanations

    words related to criminal activities or law enforcement operations.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     lur
    -0.65
     Highlands
    -0.59
    ertodd
    -0.58
    urrencies
    -0.57
    =-=-
    -0.56
    acters
    -0.56
    rocket
    -0.56
     Rosenberg
    -0.56
     rises
    -0.56
     Valley
    -0.56
    POSITIVE LOGITS
     supposed
    1.14
     accustomed
    1.02
     doing
    0.97
     aiming
    0.95
     able
    0.95
     talking
    0.93
     experiencing
    0.93
     gonna
    0.89
     undertaking
    0.88
     hoping
    0.88
    Act Density 0.118%

    No Known Activations