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

    Neuronpedia

    INDEX
    Explanations

    legal terms and legislative actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     fign
    -0.88
     doman
    -0.86
     vnd
    -0.81
     blos
    -0.81
     vns
    -0.79
     aen
    -0.78
     mef
    -0.77
     bonbons
    -0.76
     fluo
    -0.76
     waer
    -0.76
    POSITIVE LOGITS
     punishable
    0.74
     offenses
    0.73
     offences
    0.72
     felony
    0.70
     misdemeanor
    0.67
     crimes
    0.64
     offence
    0.62
     offense
    0.61
     criminal
    0.58
     Precambrian
    0.53
    Act Density 0.466%

    No Known Activations