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

    Neuronpedia

    INDEX
    Explanations

    mentions of Twitter handles related to Donald J. Trump accompanied by specific dates

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Donald J. Trump, particularly with regard to events and context surrounding his name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    axter
    -0.73
    cipline
    -0.69
    perture
    -0.68
    ãĥ¼ãĥĨ
    -0.66
     confinement
    -0.66
    eele
    -0.65
    anca
    -0.65
    BIL
    -0.64
    inarily
    -0.64
    odium
    -0.64
    POSITIVE LOGITS
     Trump
    1.23
     TRUMP
    1.10
    Trump
    0.97
    DonaldTrump
    0.93
     Donald
    0.90
    realDonaldTrump
    0.86
    TRUMP
    0.78
     Putin
    0.77
    trump
    0.74
     Bush
    0.71
    Act Density 0.020%

    No Known Activations