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

    Neuronpedia

    INDEX
    Explanations

    terms related to online fraud and cheating

    oai_token-act-pair · gpt-3.5-turbo

    contexts involving deception, fraud, and disinformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hyde
    -0.80
     curv
    -0.79
    ourses
    -0.73
     isot
    -0.68
    EVA
    -0.68
     contrace
    -0.68
    aepernick
    -0.68
    udeau
    -0.68
    etus
    -0.67
    igham
    -0.67
    POSITIVE LOGITS
     Anonymous
    0.92
     blacklist
    0.87
     perpetrated
    0.84
     scams
    0.83
     liar
    0.80
     hoax
    0.79
     scam
    0.79
     Clown
    0.76
     disinformation
    0.74
     malware
    0.74
    Act Density 0.790%

    No Known Activations