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

    Neuronpedia

    INDEX
    Explanations

    _mentions of the name "President Trump"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of President Trump

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     à¨
    -0.91
    ä¸ī
    -0.79
    âĸ¬âĸ¬
    -0.77
     CentOS
    -0.76
    à¨
    -0.71
    orig
    -0.70
    Ü
    -0.70
    à¦
    -0.69
    bred
    -0.69
    Ú
    -0.69
    POSITIVE LOGITS
    Trump
    1.08
     Trump
    1.01
    TRUMP
    0.97
     Donald
    0.95
    trump
    0.87
     TRUMP
    0.86
    Donald
    0.85
    andowski
    0.85
     dossier
    0.84
    thal
    0.82
    Act Density 0.050%

    No Known Activations