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

    Neuronpedia

    INDEX
    Explanations

    words related to corruption and unethical behavior in politics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -1.08
    geist
    -1.04
     Bard
    -0.96
    cht
    -0.95
    folk
    -0.91
     visually
    -0.91
    hari
    -0.91
     Bir
    -0.91
    externalActionCode
    -0.89
    Downloadha
    -0.89
    POSITIVE LOGITS
    itud
    1.60
    raction
    1.57
    ention
    1.48
    ensible
    1.45
    inct
    1.44
    ensions
    1.44
    ortion
    1.42
    ended
    1.40
    ract
    1.40
    ension
    1.39
    Act Density 0.770%

    No Known Activations