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

    Neuronpedia

    INDEX
    Explanations

    dates and specific events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates and events related to political or controversial topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mages
    -0.79
     Albion
    -0.78
     LTD
    -0.76
    onica
    -0.74
     guild
    -0.73
     NAD
    -0.72
     TTL
    -0.71
     Pione
    -0.70
    utic
    -0.69
    byss
    -0.69
    POSITIVE LOGITS
     tweeting
    1.26
     speeches
    1.25
     retweet
    1.20
    TRUMP
    1.13
     tweets
    1.13
    realDonaldTrump
    1.06
    Hillary
    1.05
     uttered
    1.04
     disav
    1.03
    Trump
    1.01
    Act Density 0.740%

    No Known Activations