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

    Neuronpedia

    INDEX
    Explanations

    terms related to rehabilitation and reintegration of individuals into society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /alert
    -0.14
     DIG
    -0.14
    745
    -0.14
    çĸij
    -0.13
    elp
    -0.13
    кÑĥлÑĮ
    -0.13
     actionTypes
    -0.13
    .Dispatcher
    -0.13
    itary
    -0.13
    eries
    -0.12
    POSITIVE LOGITS
     prison
    0.30
     offender
    0.29
     incarcerated
    0.28
     program
    0.28
     Prison
    0.28
     parole
    0.27
     incarceration
    0.27
     offenders
    0.27
     prisoners
    0.25
     programming
    0.25
    Act Density 0.012%

    No Known Activations