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

    Neuronpedia

    INDEX
    Explanations

    terms related to deception and falsehoods, particularly in media and narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    তথ্যসূত্র
    -0.79
     primaire
    -0.78
    tamment
    -0.77
     canzoni
    -0.75
     lær
    -0.75
     ChromeDriver
    -0.75
    BindingResult
    -0.74
     disambiguazione
    -0.72
     debout
    -0.71
    SQLiteDatabase
    -0.71
    POSITIVE LOGITS
     fake
    1.35
     Fake
    1.24
    Fake
    1.10
    fake
    1.06
     pretend
    1.03
     faux
    0.95
     Faux
    0.94
    Faux
    0.92
     false
    0.92
    Pret
    0.91
    Act Density 0.316%

    No Known Activations