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

    Neuronpedia

    INDEX
    Explanations

    details about economic and political actions related to trade agreements and government policies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     disemb
    -0.67
     deity
    -0.65
    clus
    -0.62
     unden
    -0.60
     masculine
    -0.60
     spoiler
    -0.60
    ãĤ¨ãĥ«
    -0.59
     muse
    -0.58
     cavern
    -0.57
     erotic
    -0.56
    POSITIVE LOGITS
     Meanwhile
    0.93
     Similarly
    0.93
     Likewise
    0.88
     Moreover
    0.87
     Others
    0.85
     Additionally
    0.84
     Consequently
    0.84
     Furthermore
    0.83
     Conversely
    0.83
     Ironically
    0.82
    Act Density 7.076%

    No Known Activations