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

    Neuronpedia

    INDEX
    Explanations

    mentions of "fake news" and related deceptive or misleading information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tamment
    -0.76
     debout
    -0.74
     primaire
    -0.74
     Portail
    -0.72
    NamedQueries
    -0.71
    তথ্যসূত্র
    -0.71
     volando
    -0.70
    berdayakan
    -0.70
     participaron
    -0.69
     canzoni
    -0.69
    POSITIVE LOGITS
     fake
    1.67
     Fake
    1.52
    Fake
    1.45
    fake
    1.40
     faux
    1.29
     false
    1.27
     phony
    1.18
     Faux
    1.18
     fakes
    1.17
     pretend
    1.15
    Act Density 0.227%

    No Known Activations