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

    Neuronpedia

    INDEX
    Explanations

    instances of corruption and bribery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fos
    -0.16
    artz
    -0.16
    üzel
    -0.16
    CISION
    -0.15
    coop
    -0.15
    ndata
    -0.14
    VertexAttrib
    -0.14
    prung
    -0.14
    amos
    -0.14
    Smarty
    -0.14
    POSITIVE LOGITS
     bri
    0.40
     corrupt
    0.35
     brib
    0.33
     Bri
    0.33
     corruption
    0.32
     bribery
    0.30
     corrupted
    0.29
     gifts
    0.28
     Corruption
    0.28
     Gifts
    0.25
    Act Density 0.052%

    No Known Activations