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

    Neuronpedia

    INDEX
    Explanations

    mentions of prisons and related concepts such as prison population, prison system, and prison industry

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the prison system and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lass
    -0.82
    £ı
    -0.70
    uyomi
    -0.68
    lip
    -0.64
    ãĥ£
    -0.64
    ullivan
    -0.64
    UTH
    -0.64
    lasses
    -0.64
    arkin
    -0.64
     Remastered
    -0.61
    POSITIVE LOGITS
     inmates
    1.19
     inmate
    1.14
     overcrowd
    0.97
     prison
    0.92
     prisons
    0.92
     prisoners
    0.91
    prison
    0.90
    house
    0.89
     sentences
    0.88
    planet
    0.87
    Act Density 0.055%

    No Known Activations