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

    Neuronpedia

    INDEX
    Explanations

    references to corruption and oversight in government

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç·
    -0.17
    nonnull
    -0.15
    رÙĪÙĩ
    -0.14
    MimeType
    -0.14
    \application
    -0.14
     ^{°}
    -0.14
    ä»®
    -0.14
    jee
    -0.14
    .community
    -0.14
    ndl
    -0.14
    POSITIVE LOGITS
     corruption
    0.51
     Corruption
    0.46
     corrupt
    0.41
    èħIJ
    0.40
     graft
    0.36
     bri
    0.35
    -cor
    0.35
     bribery
    0.34
     corrupted
    0.34
     Bri
    0.32
    Act Density 0.139%

    No Known Activations