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

    Neuronpedia

    INDEX
    Explanations

    phrases related to inmates and prison activities

    oai_token-act-pair · gpt-3.5-turbo

    references to inmates and their experiences within the prison system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rous
    -0.73
    OPA
    -0.72
    drive
    -0.69
    ãĥ¼ãĥ³
    -0.69
    orically
    -0.68
    jri
    -0.67
    POL
    -0.66
    ku
    -0.66
    orie
    -0.66
    neau
    -0.65
    POSITIVE LOGITS
     inmates
    0.96
    icts
    0.88
     inmate
    0.85
    iaries
    0.84
     incarcerated
    0.77
     closet
    0.75
    iary
    0.74
     Facility
    0.73
     sentenced
    0.70
     bedrooms
    0.68
    Act Density 0.020%

    No Known Activations