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

    Neuronpedia

    INDEX
    Explanations

    words related to criticism and analysis, particularly in the context of media, politics, and entertainment

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    lez
    -0.66
    eks
    -0.66
     Tomorrow
    -0.63
    hello
    -0.63
    Tonight
    -0.63
     Borough
    -0.62
    Republic
    -0.61
    oj
    -0.60
    abuse
    -0.59
     Hoy
    -0.59
    POSITIVE LOGITS
     systematically
    0.87
     remarkably
    0.86
     geographically
    0.83
     extraordinarily
    0.83
     fundamentally
    0.82
     incredibly
    0.81
     uniformly
    0.81
     consistently
    0.81
     disproportionately
    0.80
     relatively
    0.80
    Act Density 0.462%

    No Known Activations