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

    Neuronpedia

    INDEX
    Explanations

    phrases related to deception and dishonesty

    oai_token-act-pair · gpt-3.5-turbo

    statements related to dishonesty or deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Û
    -0.65
    Interstitial
    -0.65
    served
    -0.65
     oak
    -0.63
    gars
    -0.61
    ilingual
    -0.61
     bilingual
    -0.61
    favorite
    -0.61
     priced
    -0.60
     formatted
    -0.60
    POSITIVE LOGITS
     investigators
    1.12
     regulators
    0.95
     shareholders
    0.94
     Congress
    0.93
     investors
    0.90
     reporters
    0.90
     prosecutors
    0.88
     voters
    0.86
     audiences
    0.85
     congress
    0.85
    Act Density 0.301%

    No Known Activations