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

    Neuronpedia

    INDEX
    Explanations

    references to media influence and political manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lift
    -0.15
    Ñģл
    -0.14
    orde
    -0.14
     conservatism
    -0.14
    รม
    -0.14
    ectors
    -0.13
     milfs
    -0.13
    erie
    -0.13
    eron
    -0.13
    RunWith
    -0.13
    POSITIVE LOGITS
     country
    0.20
     Found
    0.19
     Koch
    0.19
     fram
    0.17
     left
    0.17
     media
    0.17
    ountry
    0.16
     economy
    0.16
     Fram
    0.16
     current
    0.16
    Act Density 0.472%

    No Known Activations