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

    Neuronpedia

    INDEX
    Explanations

    references to former President Donald Trump

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Donald Trump and Barack Obama in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨ
    -0.76
    Els
    -0.75
    PsyNetMessage
    -0.68
    Sov
    -0.67
    Offline
    -0.66
    ãĤ¯
    -0.66
     extraction
    -0.65
    driving
    -0.65
    AGES
    -0.64
    MpServer
    -0.62
    POSITIVE LOGITS
     vetoed
    1.07
     congratulated
    1.03
     convened
    1.01
     pard
    1.01
     ordered
    1.00
     toured
    0.98
     appointed
    0.96
     appoint
    0.96
     urged
    0.96
     praised
    0.95
    Act Density 0.105%

    No Known Activations