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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dishonesty and unethical behavior

    oai_token-act-pair · gpt-3.5-turbo

    references to dishonesty and deception in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irtual
    -0.77
     Feedback
    -0.76
     Impact
    -0.69
     Talks
    -0.68
    ORPG
    -0.66
    helps
    -0.65
     Factors
    -0.65
     Affect
    -0.65
     interacts
    -0.64
     Develop
    -0.64
    POSITIVE LOGITS
     Orwell
    1.16
     grotesque
    1.15
     laughable
    1.10
     treason
    1.09
     impunity
    1.09
     intolerable
    1.08
     shameless
    1.03
     pathetic
    1.02
     despicable
    1.02
     breathtaking
    1.02
    Act Density 0.630%

    No Known Activations