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

    Neuronpedia

    INDEX
    Explanations

    references to propaganda in various contexts

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

    political propaganda and manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pona
    -0.48
    \{\\
    -0.47
    uris
    -0.47
    HasColumnType
    -0.46
    EClass
    -0.46
    etes
    -0.45
     Dilemma
    -0.45
    Cerv
    -0.44
    -0.44
     spalle
    -0.44
    POSITIVE LOGITS
     propaganda
    1.91
     Propaganda
    1.76
    paganda
    1.73
     propagan
    1.38
     propa
    0.90
     propag
    0.89
     пропа
    0.79
    宣传
    0.78
     Propag
    0.76
     indoctr
    0.76
    Act Density 0.012%

    No Known Activations