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

    Neuronpedia

    INDEX
    Explanations

    mentions of people holding official titles related to authoritative positions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "director" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.66
     compr
    -0.66
     silicone
    -0.58
    âĨij
    -0.57
     lid
    -0.57
     Leafs
    -0.57
     Stain
    -0.57
    âĶĢâĶĢâĶĢâĶĢ
    -0.57
    ulz
    -0.57
     mileage
    -0.56
    POSITIVE LOGITS
    ial
    1.12
    ovie
    1.07
    ates
    1.03
    ials
    1.01
    ially
    1.00
    ate
    0.94
    general
    0.93
    ogen
    0.86
    IAL
    0.83
    iate
    0.82
    Act Density 0.040%

    No Known Activations