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

    Neuronpedia

    INDEX
    Explanations

    terms related to misinformation and propaganda

    oai_token-act-pair · gpt-3.5-turbo

    terms related to misinformation and propaganda

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imen
    -0.75
    rared
    -0.69
    airo
    -0.67
    urat
    -0.67
    onga
    -0.67
    atta
    -0.66
    cise
    -0.65
    inence
    -0.65
    atal
    -0.65
    ropri
    -0.64
    POSITIVE LOGITS
     perpetrated
    0.94
     misinformation
    0.83
     disinformation
    0.82
     spreads
    0.82
    mong
    0.78
     propag
    0.77
     hoax
    0.77
     tactics
    0.71
    ument
    0.71
     detector
    0.71
    Act Density 0.076%

    No Known Activations