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

    Neuronpedia

    INDEX
    Explanations

    references to political corruption and scandals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.71
    ArrowToggle
    -0.60
    endphp
    -0.58
    出版年
    -0.56
     PSY
    -0.52
    LookAnd
    -0.50
     Vege
    -0.49
    tanleria
    -0.49
    Tensi
    -0.48
    WriteAttribute
    -0.48
    POSITIVE LOGITS
     corruption
    1.64
     Corruption
    1.45
    Corruption
    1.42
    corruption
    1.36
     corrupt
    1.31
     Transparency
    1.16
     corrupción
    1.15
     bribery
    1.14
     anticor
    1.13
     corrup
    1.13
    Act Density 0.612%

    No Known Activations