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

    Neuronpedia

    INDEX
    Explanations

    terms related to corruption and bribery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    üzel
    -0.15
    bst
    -0.15
     libertin
    -0.14
    FieldValue
    -0.14
    icaret
    -0.14
    ws
    -0.14
    bots
    -0.14
    coop
    -0.14
     zd
    -0.14
    .getMinutes
    -0.14
    POSITIVE LOGITS
     bri
    0.36
     corrupt
    0.31
     brib
    0.31
     corruption
    0.30
     bribery
    0.29
     Bri
    0.26
     gifts
    0.26
     favors
    0.25
     Corruption
    0.25
     corrupted
    0.25
    Act Density 0.087%

    No Known Activations