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

    Neuronpedia

    INDEX
    Explanations

    references to political and government related topics, such as regulations, measures, and policy decisions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rcParams
    -0.46
    ]=="
    -0.46
     wodurch
    -0.45
     ouvriers
    -0.44
     gezien
    -0.42
     thicket
    -0.42
    RTEE
    -0.42
     насељу
    -0.41
     Grecian
    -0.39
    RTLR
    -0.39
    POSITIVE LOGITS
    ixante
    0.90
     seventy
    0.83
     eighty
    0.82
     ninety
    0.81
    thirty
    0.80
    twenty
    0.80
     thirty
    0.79
     fifty
    0.79
     priva
    0.78
     sixty
    0.78
    Act Density 0.058%

    No Known Activations