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

    Neuronpedia

    INDEX
    Explanations

    words related to corruption

    oai_token-act-pair · gpt-3.5-turbo

    instances and discussions of corruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¯¯¯¯
    -0.83
    amins
    -0.77
    Phones
    -0.75
    lee
    -0.72
    imus
    -0.71
    Dispatch
    -0.69
    Temperature
    -0.69
    cknowled
    -0.69
    emade
    -0.68
    ¯¯
    -0.67
    POSITIVE LOGITS
     corruption
    1.21
     scandals
    1.05
     corrupt
    0.93
     Corruption
    0.89
     corrupted
    0.88
     scandal
    0.87
     bribery
    0.83
    corruption
    0.81
     graft
    0.78
     restruct
    0.77
    Act Density 0.012%

    No Known Activations