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

    Neuronpedia

    INDEX
    Explanations

    terms related to political controversies and mainstream media narratives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.36
     intersper
    -0.81
     rile
    -0.73
    Tja
    -0.71
     shenan
    -0.70
     philanth
    -0.70
    verwijspagina
    -0.69
     underval
    -0.69
     allude
    -0.67
     catast
    -0.65
    POSITIVE LOGITS
     mainstream
    0.90
     alpes
    0.81
     grises
    0.75
     fides
    0.72
     fons
    0.69
     corrom
    0.69
     groupName
    0.67
     ErrorCode
    0.66
     tristes
    0.64
    omenclature
    0.64
    Act Density 0.550%

    No Known Activations