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

    Neuronpedia

    INDEX
    Explanations

    keywords related to law enforcement, incarceration, and criminal activities such as bars, prison, criminal charges, drugs, and police interactions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ctive
    -0.71
     GENERAL
    -0.59
    ALLY
    -0.55
    ULAR
    -0.53
    rious
    -0.53
    ciation
    -0.52
    actus
    -0.52
    itably
    -0.51
    2019
    -0.51
    aneous
    -0.50
    POSITIVE LOGITS
    hirt
    0.84
    hop
    0.83
    mith
    0.81
    hift
    0.77
    hops
    0.77
    manship
    0.76
    poon
    0.70
    luaj
    0.68
    hips
    0.67
    MpServer
    0.66
    Act Density 5.548%

    No Known Activations