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

    Neuronpedia

    INDEX
    Explanations

    tweets made by different individuals

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating tweets or social media posts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    士
    -0.76
    bred
    -0.70
    ulhu
    -0.66
    phal
    -0.64
    姫
    -0.61
    ricular
    -0.61
     Trials
    -0.60
    vette
    -0.59
    zik
    -0.59
    riks
    -0.59
    POSITIVE LOGITS
     "@
    0.90
    realDonaldTrump
    0.83
     hasht
    0.83
    weet
    0.83
    URL
    0.80
     tweets
    0.80
     hashtag
    0.78
    ITCH
    0.75
    Tweet
    0.75
     condol
    0.72
    Act Density 0.034%

    No Known Activations