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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governmental policies and political statements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    untled
    -0.78
    arently
    -0.73
     cryptic
    -0.72
     odd
    -0.72
     speculated
    -0.70
    umably
    -0.70
     Weird
    -0.70
    pmwiki
    -0.69
     obscure
    -0.68
    dry
    -0.68
    POSITIVE LOGITS
     patri
    1.17
     dignity
    0.99
     JUSTICE
    0.98
     democracy
    0.97
     righteousness
    0.95
     creed
    0.95
     courageous
    0.94
     compassion
    0.94
     patriot
    0.94
     courage
    0.93
    Act Density 4.024%

    No Known Activations