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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial impropriety or corruption

    oai_token-act-pair · gpt-3.5-turbo

    financial misconduct and corruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terness
    -0.88
    ãĥ´
    -0.83
    itans
    -0.75
    icol
    -0.73
    ankind
    -0.73
    ãĥ¯ãĥ³
    -0.71
    enment
    -0.70
    doi
    -0.70
    crim
    -0.70
    }}}
    -0.69
    POSITIVE LOGITS
     bribes
    1.67
     bribe
    1.42
     lavish
    1.15
     payments
    1.14
     lucrative
    1.10
     favors
    1.09
     bribery
    1.08
     gifts
    1.07
     preferential
    1.05
     loans
    1.01
    Act Density 0.497%

    No Known Activations