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

    Neuronpedia

    INDEX
    Explanations

    political and societal terms related to ideology and governance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     OFDb
    -0.71
    .*")]
    -0.67
     censiti
    -0.66
    "]);
    -0.62
     faceva
    -0.60
    ']))
    -0.59
    )_/¯
    -0.58
    '])){
    -0.57
    "]));
    -0.57
     Junio
    -0.57
    POSITIVE LOGITS
     increa
    1.06
     inappro
    1.01
     impra
    1.01
     outlander
    0.96
     kawasaki
    0.95
     suscep
    0.94
     impractica
    0.93
     disagre
    0.93
     strick
    0.93
     gsx
    0.92
    Act Density 0.404%

    No Known Activations