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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Twitter handles and related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ordinance
    -0.73
    emonium
    -0.73
     circulation
    -0.71
     ordinances
    -0.70
     Ramsey
    -0.68
     immersion
    -0.67
     Bradford
    -0.66
     conversions
    -0.66
     intest
    -0.65
     metic
    -0.64
    POSITIVE LOGITS
    realDonaldTrump
    1.16
    #$
    1.08
    @@@@@@@@
    0.98
    nat
    0.90
    TAG
    0.90
    groups
    0.90
    Home
    0.83
    hidden
    0.83
    Tweet
    0.82
    photos
    0.81
    Act Density 0.021%

    No Known Activations