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

    Neuronpedia

    INDEX
    Explanations

    statements about political activities and decisions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Colonial
    -0.61
     Vers
    -0.60
     apex
    -0.56
    ãĥ¯
    -0.56
     Conquest
    -0.56
     Plaint
    -0.56
     Dome
    -0.55
     Digest
    -0.54
     Quarterly
    -0.54
     Sussex
    -0.54
    POSITIVE LOGITS
     regretted
    1.08
     encount
    0.96
     intend
    0.94
     intends
    0.94
     intention
    0.94
     regrets
    0.92
     personally
    0.88
     wished
    0.85
    'd
    0.85
     agre
    0.81
    Act Density 2.006%

    No Known Activations