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

    Neuronpedia

    INDEX
    Explanations

    references to social media

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.80
     Templar
    -0.75
     Starr
    -0.73
     Camden
    -0.69
     Reincarn
    -0.69
     Caesar
    -0.66
     Forsaken
    -0.65
     Quart
    -0.65
    aed
    -0.65
    ellectual
    -0.64
    POSITIVE LOGITS
     platforms
    1.17
     savvy
    0.99
     outlets
    0.98
     postings
    0.97
     networks
    0.94
     campaigns
    0.92
     users
    0.90
     giants
    0.89
     feeds
    0.87
     accounts
    0.83
    Act Density 0.033%

    No Known Activations