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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal punishment, specifically sentences involving prison time

    oai_token-act-pair · gpt-3.5-turbo

    mentions of prison sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endor
    -0.82
    soDeliveryDate
    -0.80
    ãĤ¤ãĥĪ
    -0.75
    yip
    -0.74
    xy
    -0.69
    rians
    -0.69
    alter
    -0.68
    ãĥ¼ãĥĨãĤ£
    -0.68
    ãĤ¡
    -0.67
     Discord
    -0.66
    POSITIVE LOGITS
     sentences
    0.98
     sentence
    0.97
     imprisonment
    0.90
     convictions
    0.80
     imprison
    0.79
     jailed
    0.79
     manslaughter
    0.77
    agy
    0.76
     inmates
    0.75
     bail
    0.75
    Act Density 0.020%

    No Known Activations