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

    Neuronpedia

    INDEX
    Explanations

    references to fraud or scams in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itor
    -0.15
    (#)
    -0.15
    ATAR
    -0.15
    rist
    -0.14
    indered
    -0.14
     خش
    -0.14
    моÑĢ
    -0.14
     trespass
    -0.13
     GENERIC
    -0.13
    icter
    -0.13
    POSITIVE LOGITS
     scams
    0.26
     scam
    0.23
     fraud
    0.23
     lá»
    0.21
    Fra
    0.20
     frau
    0.20
    æ¬
    0.20
    fra
    0.20
     fraudulent
    0.19
     snake
    0.18
    Act Density 0.196%

    No Known Activations