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

    Neuronpedia

    INDEX
    Explanations

    assertions and statements related to deception or dishonesty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     onOptions
    -0.64
    reportWebVitals
    -0.61
    참고
    -0.60
    ColumnHeaders
    -0.59
    ]){
    -0.53
    примеча
    -0.53
    Tikang
    -0.52
    IBarButtonItem
    -0.51
    ρον
    -0.51
    ArgsConstructor
    -0.51
    POSITIVE LOGITS
     deception
    1.68
     deceiving
    1.56
     deceive
    1.55
     faking
    1.49
     fake
    1.45
     deceit
    1.43
     lie
    1.43
     deceived
    1.39
     deceptive
    1.38
     ruse
    1.38
    Act Density 0.935%

    No Known Activations