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

    Neuronpedia

    INDEX
    Explanations

    statements related to international relations and politics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     crappy
    -0.75
     nightly
    -0.69
     sucker
    -0.67
     Isles
    -0.65
     legend
    -0.64
     unlucky
    -0.64
     cousins
    -0.63
     thrill
    -0.63
     everyday
    -0.62
     fancy
    -0.62
    POSITIVE LOGITS
    Regarding
    1.33
    Lastly
    1.32
    Refer
    1.29
    Furthermore
    1.29
    Secondly
    1.21
    Finally
    1.19
    Moreover
    1.19
    Additionally
    1.17
    CONCLUS
    1.16
    Therefore
    1.09
    Act Density 0.928%

    No Known Activations