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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles to follow

    oai_token-act-pair · gpt-3.5-turbo

    references to social media platforms, particularly Twitter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©
    -0.87
    chwitz
    -0.82
    acter
    -0.81
    owship
    -0.74
    ecause
    -0.73
    Ĥª
    -0.70
    rats
    -0.70
    Args
    -0.68
    @#
    -0.68
     Klux
    -0.67
    POSITIVE LOGITS
     behalf
    1.04
     twitter
    0.91
     facebook
    0.84
     Twitter
    0.81
     YouTube
    0.78
    eday
    0.78
    shore
    0.77
     Github
    0.77
     Forbes
    0.74
     github
    0.74
    Act Density 0.088%

    No Known Activations