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

    Neuronpedia

    INDEX
    Explanations

    terms related to corrupt activities

    oai_token-act-pair · gpt-3.5-turbo

    references to corruption and related legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nee
    -0.79
    ¯¯¯¯
    -0.78
    thur
    -0.75
    imus
    -0.75
    cknowled
    -0.74
    AY
    -0.72
    amins
    -0.72
    estead
    -0.71
    leigh
    -0.69
    ocard
    -0.68
    POSITIVE LOGITS
     scandals
    1.04
     corruption
    1.00
     disproportion
    0.85
     corrupt
    0.84
     scandal
    0.84
     perpetrated
    0.83
     endemic
    0.81
     dealings
    0.79
     rife
    0.78
     corrupted
    0.78
    Act Density 0.015%

    No Known Activations