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

    Neuronpedia

    INDEX
    Explanations

    terms related to fraud and fraudulent activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipop
    -0.17
    endet
    -0.16
    ezi
    -0.15
    aná
    -0.15
    кап
    -0.15
     доÑĤ
    -0.15
    errupted
    -0.14
    íĶ½
    -0.14
    imuth
    -0.14
    terdam
    -0.14
    POSITIVE LOGITS
     false
    0.28
     kick
    0.27
     straw
    0.26
     scheme
    0.25
     Scheme
    0.23
     falsely
    0.21
     schemes
    0.21
     conspir
    0.21
    scheme
    0.21
     ph
    0.20
    Act Density 0.026%

    No Known Activations