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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures and activities regarding potential collusion between political campaigns and foreign governments, specifically Russia

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ç¥ŀ
    -0.95
    enment
    -0.84
    }}}
    -0.81
    iku
    -0.81
    ciation
    -0.81
    vation
    -0.81
     univers
    -0.79
     roar
    -0.77
    liga
    -0.76
    ãĤ¦ãĤ¹
    -0.75
    POSITIVE LOGITS
     clandestine
    1.24
     covert
    1.23
     allegedly
    1.23
     illicit
    1.21
     alleged
    1.19
     CIA
    1.18
     espionage
    1.15
     Manafort
    1.15
     secretly
    1.13
     bribes
    1.13
    Act Density 3.866%

    No Known Activations