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

    Neuronpedia

    INDEX
    Explanations

    terms related to corruption, bribery, and financial misconduct

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bribery and corruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Trend
    -0.84
    LAN
    -0.81
    nesota
    -0.81
    Dub
    -0.80
     Nationwide
    -0.80
    ISS
    -0.76
    ART
    -0.76
    dar
    -0.75
    States
    -0.74
    Cloud
    -0.73
    POSITIVE LOGITS
     bribes
    1.45
     bribe
    1.44
     bribery
    1.02
     induce
    0.87
     extortion
    0.83
     bait
    0.79
     discounts
    0.79
     disgu
    0.78
     barg
    0.77
     outwe
    0.74
    Act Density 0.004%

    No Known Activations