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

    Neuronpedia

    INDEX
    Explanations

    words related to fraudulent activities or accusations

    oai_token-act-pair · gpt-3.5-turbo

    references to fraudulent activities or fraud-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.75
    ŃĶ
    -0.68
     Ange
    -0.66
    cki
    -0.61
     Despair
    -0.60
     Borders
    -0.60
     Aram
    -0.58
     Afric
    -0.58
     Quartz
    -0.57
    %"
    -0.57
    POSITIVE LOGITS
    ulent
    1.73
    ulence
    1.62
    sters
    1.41
    ster
    1.31
    ul
    1.10
    ulus
    1.01
    ulators
    0.96
    inals
    0.94
    raud
    0.93
     perpetrated
    0.92
    Act Density 0.039%

    No Known Activations