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

    Neuronpedia

    INDEX
    Explanations

    references to or descriptions of social media

    oai_token-act-pair · gpt-3.5-turbo

    references to social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Templar
    -0.79
     Starr
    -0.76
     Forsaken
    -0.70
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.67
     Venom
    -0.67
     Camden
    -0.66
     Tripoli
    -0.66
    20439
    -0.65
     Caesar
    -0.65
    ãĥ´
    -0.65
    POSITIVE LOGITS
     platforms
    1.03
     savvy
    0.93
    eval
    0.92
     outlets
    0.91
     postings
    0.90
     networks
    0.83
     accounts
    0.82
     giants
    0.81
     users
    0.80
     outage
    0.79
    Act Density 0.027%

    No Known Activations