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

    Neuronpedia

    INDEX
    Explanations

    terms related to corruption and regulatory compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amon
    -0.19
    inux
    -0.16
    idel
    -0.15
    andbox
    -0.15
    adr
    -0.15
     Pew
    -0.15
    hud
    -0.15
    itech
    -0.15
    Äįas
    -0.15
    инÑĥв
    -0.14
    POSITIVE LOGITS
     Bri
    0.40
     bribery
    0.37
     bri
    0.37
     brib
    0.32
     corrupt
    0.27
     corruption
    0.25
     antib
    0.24
     Anti
    0.23
     Gifts
    0.23
     anti
    0.23
    Act Density 0.004%

    No Known Activations