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

    Neuronpedia

    INDEX
    Explanations

    references to trade policies and tariffs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Donald Trump

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    explique
    -0.38
     estacion
    -0.37
     sepol
    -0.34
     çik
    -0.34
    spender
    -0.34
     escon
    -0.33
     phối
    -0.33
     pratic
    -0.32
     presta
    -0.32
    Shoulder
    -0.32
    POSITIVE LOGITS
     Trump
    1.55
    Trump
    1.46
     Donald
    1.23
    Donald
    1.22
    trump
    1.09
     donald
    1.05
     ترام
    1.03
     DONALD
    0.99
    特朗普
    0.98
     trump
    0.98
    Act Density 0.197%

    No Known Activations