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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and legislative matters, as well as mentions of specific locations and organizations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    chwitz
    -0.62
     havoc
    -0.59
     measles
    -0.56
     shalt
    -0.56
     TAMADRA
    -0.55
     Heist
    -0.53
     æľ
    -0.53
    ciation
    -0.52
     Unloaded
    -0.52
    resy
    -0.52
    POSITIVE LOGITS
     partners
    0.91
     reviewers
    0.90
     onlook
    0.90
     representatives
    0.89
     allies
    0.89
     colleagues
    0.89
     authorities
    0.88
     producers
    0.88
     officials
    0.86
     stakeholders
    0.86
    Act Density 1.151%

    No Known Activations